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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 21746
    Prev
    Next
    INDEX
    Explanations

    the specific term "Congressman" or similar variations in text

    oai_token-act-pair · gpt-3.5-turbo

    references to congressmen

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phal
    -0.84
    istically
    -0.78
    kus
    -0.71
     Dragonbound
    -0.70
    condition
    -0.70
    istic
    -0.70
    sea
    -0.68
    ties
    -0.66
     Devils
    -0.65
    ition
    -0.64
    POSITIVE LOGITS
     Congressman
    0.98
     congressman
    0.96
     Ike
    0.80
     Issa
    0.76
    onse
    0.73
     Lyndon
    0.71
    REC
    0.69
    aii
    0.69
     Franch
    0.68
    rint
    0.67
    Activations Density 0.009%

    No Known Activations