© 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. 10-RES-JB
    11. 20329
    Prev
    Next
    INDEX
    Explanations

    phrases related to entering agreements, partnerships, or competitions

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    attribute
    -0.65
    obe
    -0.64
    cks
    -0.64
    killer
    -0.63
    killers
    -0.62
    roller
    -0.62
    bara
    -0.61
    die
    -0.58
    iggs
    -0.58
    alm
    -0.58
    POSITIVE LOGITS
    prising
    1.42
     into
    1.19
    tain
    1.08
    prises
    1.03
    prise
    1.01
     INTO
    1.01
    TAIN
    0.96
    tained
    0.94
    into
    0.91
    taining
    0.90
    Activations Density 0.038%

    No Known Activations