© 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. 10-RES-JB
    11. 7897
    Prev
    Next
    INDEX
    Explanations

    phrases related to uncertainty or potential consequences

    oai_token-act-pair · gpt-3.5-turbo

    references to societal issues or concerns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     in
    -0.58
    behind
    -0.55
     nowhere
    -0.51
    enance
    -0.51
     everywhere
    -0.50
     captcha
    -0.48
     anywhere
    -0.48
     embr
    -0.48
     elsewhere
    -0.47
     rejecting
    -0.47
    POSITIVE LOGITS
    itably
    0.65
    etime
    0.64
    idth
    0.63
    zees
    0.62
    apest
    0.61
    ãģĨ
    0.59
    versible
    0.59
    untarily
    0.58
    daq
    0.58
    ittee
    0.58
    Activations Density 0.711%

    No Known Activations