© 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. 7701
    Prev
    Next
    INDEX
    Explanations

    instances of individuals pretending to be something they are not

    oai_token-act-pair · gpt-3.5-turbo

    instances of people or entities assuming false identities

    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
     sugg
    -0.84
    many
    -0.80
    Reviewer
    -0.78
     roundup
    -0.75
     disproportion
    -0.69
    ucket
    -0.68
    most
    -0.65
     cumulative
    -0.65
    raq
    -0.64
     accum
    -0.64
    POSITIVE LOGITS
     invincible
    0.75
     Nicarag
    0.72
    aphael
    0.72
     clown
    0.70
     Egyptian
    0.70
     Hermes
    0.69
     CGI
    0.69
     Nak
    0.69
     harmless
    0.68
     Martian
    0.68
    Activations Density 0.177%

    No Known Activations