© 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. 3-RES-JB
    11. 14723
    Prev
    Next
    INDEX
    Explanations

    physical actions or states

    oai_token-act-pair · gpt-3.5-turbo

    references to physical states or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ered
    -0.75
     Tul
    -0.73
    oi
    -0.72
    ilts
    -0.70
     Parables
    -0.69
     Transparency
    -0.68
     Chance
    -0.67
     Doctrine
    -0.67
     Aval
    -0.67
    ffic
    -0.67
    POSITIVE LOGITS
    anguage
    0.81
     assaulted
    0.81
     speaking
    0.77
     handic
    0.75
     cumbers
    0.75
     assaulting
    0.75
     altercation
    0.73
     incapable
    0.73
     destro
    0.71
    gamer
    0.71
    Activations Density 0.006%

    No Known Activations