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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 45887
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political issues

    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
    756
    +0.10
    0.7%
    103
    +0.07
    0.5%
    705
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.10
    -0.11
    547
    +0.07
    0.04
    327
    +0.07
    0.08
    Negative Logits
    father
    -0.43
     Tray
    -0.42
     Scarlett
    -0.42
     Riverside
    -0.41
     Mothers
    -0.41
     Cron
    -0.41
    live
    -0.41
     VG
    -0.40
     Strawberry
    -0.40
     Patty
    -0.40
    POSITIVE LOGITS
    initions
    0.50
    ilk
    0.49
    rero
    0.45
    hooting
    0.45
    .''.
    0.43
    ember
    0.43
    rained
    0.43
    worldly
    0.42
    egu
    0.42
    .�
    0.41
    Activations Density 7.763%

    No Known Activations