© 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. 4905
    Prev
    Next
    INDEX
    Explanations

    titles or occupations related to media personalities and professionals

    oai_token-act-pair · gpt-3.5-turbo

    titles or roles related to occupations and professions

    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
    sth
    -0.81
    lest
    -0.76
    inth
    -0.74
    nect
    -0.74
    ixel
    -0.72
    ãĥ´ãĤ¡
    -0.66
    Legend
    -0.65
    amaz
    -0.65
    omaly
    -0.64
    aman
    -0.63
    POSITIVE LOGITS
     alike
    1.49
     respectively
    1.47
     combo
    0.86
     extraord
    0.76
     LLP
    0.73
     sectors
    0.73
    SPONSORED
    0.72
     depending
    0.71
     combination
    0.69
    depending
    0.68
    Activations Density 0.449%

    No Known Activations