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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 15492
    Prev
    Next
    INDEX
    Explanations

    terms related to personal responsibility and action

    oai_token-act-pair · gpt-3.5-turbo

    terms related to accountability and regulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faintly
    -0.74
     distinctly
    -0.73
     definitely
    -0.73
     curiously
    -0.73
    usually
    -0.71
     generally
    -0.71
     equally
    -0.70
     cautiously
    -0.69
     specifically
    -0.69
    psey
    -0.68
    POSITIVE LOGITS
    ãĥīãĥ©
    0.81
    ourced
    0.74
    ifiable
    0.69
    Initialized
    0.69
    arded
    0.66
     fault
    0.66
    ãĥ£
    0.64
    rez
    0.64
    yth
    0.64
    uga
    0.63
    Activations Density 0.715%

    No Known Activations