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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 22883
    Prev
    Next
    INDEX
    Explanations

    references to the terrorist group "IS" or "ISIS"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Islamic State (IS)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    issance
    -0.87
     Trace
    -0.78
    Reviewer
    -0.72
     Brach
    -0.69
     Pry
    -0.69
     Seym
    -0.68
    ruciating
    -0.67
     Hundred
    -0.66
     Hearth
    -0.65
    rities
    -0.64
    POSITIVE LOGITS
    SU
    1.04
    FP
    1.02
    Os
    0.97
    SI
    0.94
    BN
    0.94
    AF
    0.91
    OD
    0.91
    eq
    0.90
    PUT
    0.86
    AB
    0.84
    Activations Density 0.014%

    No Known Activations