© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 17435
    Prev
    Next
    INDEX
    Explanations

    number abbreviations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "IND" which likely represents a specific term relevant to the context of the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.73
    asing
    -0.70
    redit
    -0.69
    chery
    -0.69
    ases
    -0.68
    bara
    -0.68
    ibling
    -0.66
    ctor
    -0.66
    arters
    -0.65
     iso
    -0.65
    POSITIVE LOGITS
    OTO
    0.82
    NESS
    0.80
    ERG
    0.79
    IONS
    0.78
    ION
    0.77
    INESS
    0.75
    ERS
    0.74
    IB
    0.74
    DIT
    0.73
    ITION
    0.73
    Activations Density 0.010%

    No Known Activations