© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 36613
    Prev
    Next
    INDEX
    Explanations

    quantitative information related to food consumption and economic vulnerability

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    71
    +0.10
    0.6%
    393
    +0.10
    0.5%
    448
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.10
    0.25
    608
    +0.10
    0.19
    362
    +0.07
    0.14
    Negative Logits
    haps
    -0.63
    ²¾
    -0.62
     Psychiat
    -0.57
    may
    -0.54
     pse
    -0.54
    spir
    -0.52
     vigilant
    -0.50
    aji
    -0.50
     Liberation
    -0.50
    icion
    -0.49
    POSITIVE LOGITS
    tein
    0.85
     brunt
    0.66
     blame
    0.61
     reins
    0.59
    ussian
    0.55
    ãĤ£
    0.52
    automatic
    0.52
    holm
    0.51
    ãĥ³
    0.51
    çĶ°
    0.51
    Activations Density 9.540%

    No Known Activations