© 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. 7439
    Prev
    Next
    INDEX
    Explanations

    alphabetical terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of an alphabet

    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
    arte
    -0.84
    db
    -0.68
     Anderson
    -0.66
    roxy
    -0.65
    Donnell
    -0.65
    erest
    -0.64
    PLIED
    -0.64
    dt
    -0.64
    private
    -0.64
    rings
    -0.64
    POSITIVE LOGITS
     alphabet
    1.26
    ical
    1.19
    ically
    1.12
     soup
    0.94
    icals
    0.91
    abet
    0.88
    alogy
    0.87
    icter
    0.86
    ophone
    0.86
    matical
    0.81
    Activations Density 0.012%

    No Known Activations