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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 13935
    Prev
    Next
    INDEX
    Explanations

    phrases related to opinions and perspectives

    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
    447
    +0.15
    0.7%
    163
    +0.09
    0.5%
    581
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.15
    0.14
    184
    +0.09
    0.04
    70
    +0.09
    0.12
    Negative Logits
    qus
    -0.69
    OGR
    -0.60
     Advertisement
    -0.57
    rer
    -0.56
    pelling
    -0.56
    eln
    -0.55
    iti
    -0.54
    agram
    -0.52
    rers
    -0.52
     Additional
    -0.52
    POSITIVE LOGITS
     except
    0.99
     alike
    0.81
    Tes
    0.78
    except
    0.76
     equally
    0.76
     imaginable
    0.75
    winner
    0.67
    ãĤ«
    0.61
    lishes
    0.57
    endif
    0.56
    Activations Density 14.288%

    No Known Activations