© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios or questions about potential actions

    oai_token-act-pair · gpt-3.5-turbo

    hypothetical questions or scenarios about actions and consequences

    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
     lately
    -0.65
    acca
    -0.64
    è¦ļéĨĴ
    -0.61
     prepares
    -0.58
    icus
    -0.57
    ackets
    -0.56
    emis
    -0.55
     \'
    -0.55
    beta
    -0.53
    haw
    -0.53
    POSITIVE LOGITS
    enance
    0.87
     if
    0.76
    ivably
    0.76
    «
    0.74
    would
    0.72
    aeda
    0.71
    renheit
    0.68
     differently
    0.67
    Had
    0.67
     unthinkable
    0.66
    Activations Density 0.426%

    No Known Activations