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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 5099
    Prev
    Next
    INDEX
    Explanations

    HTML-related terms and programming codes

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and code-related elements

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

    No Comments

    Negative Logits
    natureconservancy
    -0.74
    cutting
    -0.71
     belts
    -0.70
     scrut
    -0.69
     Yel
    -0.67
    én
    -0.66
    ankind
    -0.66
    arag
    -0.66
    eger
    -0.64
    erella
    -0.64
    POSITIVE LOGITS
    _
    1.11
    __
    1.03
    _-_
    0.93
    ___
    0.77
    ()
    0.76
    ._
    0.69
    _(
    0.68
    oca
    0.67
    _.
    0.66
    =(
    0.65
    Activations Density 0.107%

    No Known Activations