© 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. 31637
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to sports, particularly football and basketball

    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
    466
    +0.11
    0.5%
    489
    +0.10
    0.5%
    92
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    466
    +0.11
    0.10
    98
    +0.10
    0.13
    514
    +0.09
    0.06
    Negative Logits
    DERR
    -0.72
     layouts
    -0.61
     Clover
    -0.61
     quantity
    -0.60
    çĶ°
    -0.60
    upon
    -0.59
     spine
    -0.59
    çīĪ
    -0.58
    ATTLE
    -0.58
    ORED
    -0.58
    POSITIVE LOGITS
    haps
    1.12
    ongyang
    1.08
    enza
    0.94
    itive
    0.85
    inent
    0.83
    iminary
    0.83
    orius
    0.82
    umatic
    0.82
    sth
    0.80
    eworthy
    0.80
    Activations Density 7.115%

    No Known Activations