© 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. 10008
    Prev
    Next
    INDEX
    Explanations

    mentions of additional or bonus items or features

    oai_token-act-pair · gpt-3.5-turbo

    instances of additional information or details in lists

    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
    Really
    -0.86
    ãĤ¦ãĤ¹
    -0.79
    Sure
    -0.71
    cffffcc
    -0.71
    reason
    -0.70
    Certainly
    -0.70
    é¾įå¥ij士
    -0.69
    Yet
    -0.69
     Really
    -0.67
    really
    -0.67
    POSITIVE LOGITS
     we
    0.87
     there
    0.73
     including
    0.72
     entrants
    0.70
     researchers
    0.69
     representatives
    0.69
     participants
    0.68
     astronomers
    0.65
     archaeologists
    0.64
     they
    0.63
    Activations Density 0.345%

    No Known Activations