© 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 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. 6-RES-JB
    11. 14690
    Prev
    Next
    INDEX
    Explanations

    variables or data specifications in a structured format, particularly within scripts or code snippets

    oai_token-act-pair · gpt-3.5-turbo

    structured data formats, particularly those resembling JSON or similar markup languages

    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
     compliment
    -0.71
    coat
    -0.68
    \\\\\\\\
    -0.63
     Coat
    -0.60
     itself
    -0.59
    rous
    -0.59
    ISON
    -0.58
    estine
    -0.58
     behold
    -0.56
    Äĩ
    -0.56
    POSITIVE LOGITS
    everal
    0.88
    ettings
    0.87
    edIn
    0.79
    76561
    0.74
    peed
    0.74
     Tags
    0.73
    txt
    0.73
    ource
    0.72
    hare
    0.71
    noxious
    0.71
    Activations Density 0.380%

    No Known Activations