© 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. 2951
    Prev
    Next
    INDEX
    Explanations

    actions, steps, or instructions in a sequential manner

    oai_token-act-pair · gpt-3.5-turbo

    actions or events that involve completion or results of tasks

    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
    ï¸ı
    -0.66
    ãĥĩãĤ£
    -0.55
    conservancy
    -0.53
     (@
    -0.52
    absolutely
    -0.51
     Belfast
    -0.51
    unless
    -0.51
    isoft
    -0.51
    never
    -0.51
     whistleblower
    -0.50
    POSITIVE LOGITS
     however
    0.82
     completes
    0.71
    ward
    0.69
    ,
    0.63
    ratulations
    0.63
    tions
    0.61
     retrie
    0.59
    Result
    0.59
     there
    0.58
     though
    0.58
    Activations Density 0.467%

    No Known Activations