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. 8-RES-JB
    6. 14756
    Prev
    Next
    INDEX
    Explanations

    concerns about consequences and actions related to policy decisions

    oai_token-act-pair · gpt-3.5-turbo

    quotes and phrases that express criticism or condemnation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kitten
    -0.69
     GG
    -0.63
     aux
    -0.61
     nick
    -0.58
     *)
    -0.58
     metic
    -0.58
     Zeal
    -0.57
     BS
    -0.57
    uta
    -0.57
     ãģ
    -0.56
    POSITIVE LOGITS
     according
    0.97
     said
    0.97
     says
    0.92
    ,,,,
    0.82
    according
    0.81
     experts
    0.79
    ?,
    0.79
    ',"
    0.77
     analysts
    0.75
    ],"
    0.73
    Activations Density 1.007%

    No Known Activations