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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5636
    Prev
    Next
    INDEX
    Explanations

    pronouns or nouns referring to persons or groups

    oai_token-act-pair · gpt-3.5-turbo

    pronouns indicating collective or individual agency

    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
    aukee
    -0.68
    yip
    -0.65
     Aid
    -0.63
     Nelson
    -0.63
     Offense
    -0.62
     Balls
    -0.62
    OWER
    -0.61
    alky
    -0.61
    Skip
    -0.60
     Distance
    -0.60
    POSITIVE LOGITS
    'll
    1.25
     consequently
    1.07
    've
    1.03
    're
    1.00
     accordingly
    0.98
     shouldn
    0.98
     therefore
    0.95
     certainly
    0.93
    'd
    0.91
    pher
    0.87
    Activations Density 0.179%

    No Known Activations