Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34167
    Prev
    Next
    INDEX
    Explanations

    sentences related to communication surveillance, phone calls, and text messages

    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
    +0.23
    1.2%
    497
    +0.10
    0.5%
    132
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.23
    0.21
    51
    +0.10
    0.13
    132
    +0.10
    0.10
    Negative Logits
    Stud
    -0.61
    Cola
    -0.54
    INAL
    -0.54
    BIL
    -0.54
    coat
    -0.53
    jury
    -0.52
     forestry
    -0.52
    stad
    -0.52
    ANC
    -0.51
    ALLY
    -0.51
    POSITIVE LOGITS
    mith
    0.84
    linger
    0.81
     exchanged
    0.77
     intercepted
    0.75
    hare
    0.74
     Emails
    0.73
     overheard
    0.71
    cape
    0.71
     originating
    0.71
    peak
    0.71
    Activations Density 11.033%

    No Known Activations