© 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. 121
    Prev
    Next
    INDEX
    Explanations

    hash tags

    oai_token-act-pair · gpt-3.5-turbo

    the programming language C#

    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
     Gors
    -0.79
     Karin
    -0.70
    vation
    -0.68
     Vie
    -0.68
     Glas
    -0.67
     furthe
    -0.67
     retired
    -0.67
     circulation
    -0.64
     solitary
    -0.64
     sew
    -0.61
    POSITIVE LOGITS
    define
    1.11
    !/
    1.06
    wcsstore
    0.95
    HY
    0.93
    endif
    0.87
    DIV
    0.82
    @#
    0.81
    Fire
    0.78
    License
    0.78
    DonaldTrump
    0.78
    Activations Density 0.008%

    No Known Activations