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. 7-RES-JB
    6. 6858
    Prev
    Next
    INDEX
    Explanations

    mentions of HR (human resources) departments or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to human rights topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĸ¬
    -0.73
    cart
    -0.70
     Albion
    -0.66
    forth
    -0.65
     Homo
    -0.63
    coni
    -0.62
     Tycoon
    -0.61
    kick
    -0.60
    eers
    -0.60
    slow
    -0.59
    POSITIVE LOGITS
    RR
    0.96
    DP
    0.92
    adish
    0.92
    LIN
    0.90
    anging
    0.89
    OME
    0.87
    RI
    0.86
    OUGH
    0.86
    UN
    0.84
    ANGE
    0.83
    Activations Density 0.015%

    No Known Activations