© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 4566
    Prev
    Next
    INDEX
    Explanations

    mentions of personal attributes or situations related to individuals

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to personal relationships

    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
    ibaba
    -0.80
    netflix
    -0.80
    igate
    -0.79
    ildo
    -0.78
    isode
    -0.77
    Downloadha
    -0.73
    Reviewer
    -0.72
    aneers
    -0.70
    okes
    -0.69
    nets
    -0.69
    POSITIVE LOGITS
     own
    1.72
     inability
    1.45
     unwillingness
    1.28
     inexper
    1.27
     insistence
    1.27
     lack
    1.22
     willingness
    1.20
     penchant
    1.20
     reluctance
    1.20
     absence
    1.13
    Activations Density 0.240%

    No Known Activations