© 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. 14823
    Prev
    Next
    INDEX
    Explanations

    phrases related to the top portion of objects or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to the concepts of "top" and "bottom" in various contexts

    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
    naires
    -0.82
    naire
    -0.77
    ãĥīãĥ©
    -0.73
     hunger
    -0.70
    uld
    -0.70
    ibr
    -0.64
    adier
    -0.63
     Pell
    -0.63
    vacc
    -0.62
    ettel
    -0.62
    POSITIVE LOGITS
    most
    1.19
    bottom
    0.86
     membrane
    0.77
    hesis
    0.75
     pane
    0.75
     layer
    0.73
    board
    0.73
    stroke
    0.72
    mast
    0.72
     casing
    0.71
    Activations Density 0.039%

    No Known Activations