© 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. 1-RES-JB
    11. 16347
    Prev
    Next
    INDEX
    Explanations

    mentions of support or assistance

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "supp" in various forms, frequently associated with support or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rated
    -0.78
    ãĥīãĥ©ãĤ´ãĥ³
    -0.74
    FINE
    -0.72
    ERO
    -0.67
    AMS
    -0.66
     stink
    -0.65
     Abyssal
    -0.65
    RANT
    -0.65
    ANG
    -0.64
    MER
    -0.64
    POSITIVE LOGITS
    Supp
    0.95
    orter
    0.93
    supp
    0.90
     Supp
    0.87
    orters
    0.86
    lied
    0.82
    lements
    0.82
    ivably
    0.82
     confir
    0.81
    zsche
    0.74
    Activations Density 0.007%

    No Known Activations