© 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. 4-RES-JB
    11. 4231
    Prev
    Next
    INDEX
    Explanations

    USB Type-C connectors

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of technology or specifications

    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
    romeda
    -0.85
    ILLE
    -0.84
    rawdownloadcloneembedreportprint
    -0.79
    olulu
    -0.75
    姫
    -0.73
    itational
    -0.69
    ordial
    -0.68
    ITNESS
    -0.68
    utherford
    -0.66
     GOODMAN
    -0.66
    POSITIVE LOGITS
    faces
    1.14
    face
    1.03
    ahead
    0.82
    casting
    0.76
    Error
    0.73
    forms
    0.69
    etter
    0.67
    classes
    0.66
    oho
    0.65
    ology
    0.64
    Activations Density 0.015%

    No Known Activations