© 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. 6-RES-JB
    11. 19751
    Prev
    Next
    INDEX
    Explanations

    technological instructions or specifications identified by the "i.e." abbreviation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and sentence-ending elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thal
    -0.82
    ILA
    -0.67
    thren
    -0.64
    inav
    -0.63
    SPONSORED
    -0.62
    ĪĴ
    -0.62
    Anyway
    -0.61
    ims
    -0.60
    ishes
    -0.59
    aughs
    -0.59
    POSITIVE LOGITS
    âĢ¢âĢ¢
    0.73
    dropping
    0.69
     ours
    0.68
    76561
    0.68
     Canaveral
    0.68
    worth
    0.66
    calling
    0.64
    feeding
    0.61
    mma
    0.60
    cru
    0.60
    Activations Density 0.039%

    No Known Activations