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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 15703
    Prev
    Next
    INDEX
    Explanations

    mentions of politicians with the title of "congressman" followed by their names

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "congressman."

    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
    phal
    -0.88
    istically
    -0.85
    istic
    -0.79
    condition
    -0.72
    kus
    -0.70
     paras
    -0.70
    word
    -0.70
    zees
    -0.70
     Dragonbound
    -0.69
    ologically
    -0.67
    POSITIVE LOGITS
     Congressman
    0.89
     congressman
    0.89
     Issa
    0.83
     Ike
    0.82
     Franch
    0.79
    ublic
    0.73
     Nixon
    0.71
     Lyndon
    0.71
    å°Ĩ
    0.70
    resents
    0.70
    Activations Density 0.026%

    No Known Activations