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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 6-RES-JB
    11. 5518
    Prev
    Next
    INDEX
    Explanations

    terms related to specific actions or commands in technology or contexts where precision and detail are important

    oai_token-act-pair · gpt-3.5-turbo

    specific technical terms or identifiers in a context that may involve software or data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     charism
    -0.78
    oho
    -0.75
    ridges
    -0.69
    ij士
    -0.69
    castle
    -0.64
    chuk
    -0.63
    İ
    -0.63
    intelligence
    -0.63
    ike
    -0.63
     sovere
    -0.62
    POSITIVE LOGITS
    xual
    0.81
    lihood
    0.73
     APR
    0.71
    ():
    0.70
     Vict
    0.67
    REDACTED
    0.64
    /(
    0.63
     Kingdoms
    0.63
     sqor
    0.63
    ().
    0.63
    Activations Density 0.797%

    No Known Activations