© 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. 7-RES-JB
    11. 6410
    Prev
    Next
    INDEX
    Explanations

    references to self-identification or distancing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases related to creating distance or separation

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vil
    -0.67
    heny
    -0.67
    onal
    -0.67
    origin
    -0.65
     Federation
    -0.62
     Rail
    -0.60
     Fulton
    -0.59
    nic
    -0.59
     IL
    -0.59
    ouring
    -0.58
    POSITIVE LOGITS
    selves
    0.89
    DragonMagazine
    0.77
    gypt
    0.76
    é¾įåĸļ士
    0.76
     territ
    0.75
    æ³
    0.73
     tremend
    0.70
     creatively
    0.69
     anew
    0.69
    anke
    0.69
    Activations Density 0.041%

    No Known Activations