© 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
    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. 16413
    Prev
    Next
    INDEX
    Explanations

    words related to analyzing or dissecting information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "break down" in various contexts

    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
    mong
    -0.77
     endors
    -0.73
    inen
    -0.72
    ught
    -0.71
    jab
    -0.70
    athi
    -0.64
    utz
    -0.64
    ndra
    -0.63
    arak
    -0.63
    WI
    -0.63
    POSITIVE LOGITS
    stairs
    0.99
    river
    0.93
    sheets
    0.82
    graded
    0.71
     stairs
    0.71
    olid
    0.68
    foundation
    0.67
    grading
    0.67
    oded
    0.66
    pour
    0.66
    Activations Density 0.015%

    No Known Activations