© 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. 35095
    Prev
    Next
    INDEX
    Explanations

    references to specific names or titles of people

    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
    +0.13
    0.5%
    444
    +0.13
    0.5%
    326
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.13
    0.07
    319
    +0.13
    0.06
    444
    +0.13
    0.04
    Negative Logits
    ancies
    -0.96
    ted
    -0.85
    TING
    -0.83
     unlaw
    -0.82
    alls
    -0.82
    anging
    -0.81
    terness
    -0.79
    OFF
    -0.78
    TY
    -0.78
    picking
    -0.77
    POSITIVE LOGITS
    eus
    1.36
    estro
    1.35
    qua
    1.18
    esthesia
    1.13
    ñ
    1.09
    ña
    1.07
    ppa
    1.06
    pl
    1.05
    pered
    1.05
    ignt
    1.03
    Activations Density 5.051%

    No Known Activations