© 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. 10111
    Prev
    Next
    INDEX
    Explanations

    terms indicating contrast or contradiction

    oai_token-act-pair · gpt-3.5-turbo

    the word "Though" as a transition signal in a narrative

    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
     cryst
    -0.67
    isible
    -0.67
    pta
    -0.64
     answ
    -0.64
    taboola
    -0.63
    enture
    -0.63
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.63
    ared
    -0.62
     GEAR
    -0.61
     bead
    -0.60
    POSITIVE LOGITS
    ts
    1.28
    tons
    1.15
    ton
    0.87
    terness
    0.82
    chery
    0.78
     acknowledging
    0.78
    ering
    0.75
    ial
    0.75
    clair
    0.74
    lihood
    0.73
    Activations Density 0.022%

    No Known Activations