© 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. 8-RES-JB
    11. 18584
    Prev
    Next
    INDEX
    Explanations

    locations or directional words (e.g., "across," "from") in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "across" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nery
    -0.76
    etic
    -0.70
    FORE
    -0.69
    spot
    -0.63
    rw
    -0.61
    ENC
    -0.58
    nce
    -0.57
    Parents
    -0.57
    getic
    -0.57
     HELP
    -0.57
    POSITIVE LOGITS
    roads
    0.83
    atform
    0.77
     rooft
    0.74
    side
    0.72
    hang
    0.71
    flow
    0.70
    ĸļ
    0.67
    urst
    0.67
     paths
    0.66
    halla
    0.66
    Activations Density 0.027%

    No Known Activations