© 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. 0-RES-JB
    11. 12060
    Prev
    Next
    INDEX
    Explanations

    phrases related to proximity or location

    oai_token-act-pair · gpt-3.5-turbo

    references or mentions of actions or events that occur "behind" something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    types
    -0.60
    ategor
    -0.59
    Attempts
    -0.59
    mint
    -0.58
    regn
    -0.58
    rage
    -0.57
    oked
    -0.56
    gain
    -0.56
    limit
    -0.56
     weights
    -0.55
    POSITIVE LOGITS
     behind
    3.72
    behind
    2.87
     Behind
    2.63
    Behind
    1.88
     underneath
    1.37
     beneath
    1.32
     backstage
    1.13
     ahead
    1.11
     inside
    1.10
     beside
    1.06
    Activations Density 0.037%

    No Known Activations