© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9244
    Prev
    Next
    INDEX
    Explanations

    terms related to technical or scientific concepts, particularly in the fields of genomics and technology

    oai_token-act-pair · gpt-3.5-turbo

    terms indicating completeness or entirety

    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
    apa
    -0.77
    Engineers
    -0.66
    negie
    -0.63
    inches
    -0.62
    Chance
    -0.62
    ERSON
    -0.62
    ONY
    -0.61
    _-_
    -0.61
    IENCE
    -0.61
    nw
    -0.61
    POSITIVE LOGITS
    foundland
    0.65
    hood
    0.61
    ness
    0.60
     periphery
    0.60
    bies
    0.59
    izers
    0.58
     rune
    0.56
     casing
    0.56
    noxious
    0.56
     sided
    0.56
    Activations Density 0.820%

    No Known Activations