© 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. 7538
    Prev
    Next
    INDEX
    Explanations

    texts related to the music industry

    oai_token-act-pair · gpt-3.5-turbo

    references to various industries

    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
    Ter
    -0.68
    Vel
    -0.67
    iar
    -0.67
    tein
    -0.67
    hiro
    -0.65
     Tol
    -0.65
    å¦
    -0.65
    imm
    -0.65
    Ô
    -0.63
    Nar
    -0.62
    POSITIVE LOGITS
    naire
    0.78
    ousel
    0.76
     marketplace
    0.76
    eers
    0.73
    atics
    0.69
    naires
    0.69
     landscape
    0.69
    mma
    0.69
     Dollar
    0.69
     spotlight
    0.69
    Activations Density 0.350%

    No Known Activations