© 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. 22626
    Prev
    Next
    INDEX
    Explanations

    instances of the word "rift."

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "shift."

    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
     Hanson
    -0.70
    gdala
    -0.68
     Lara
    -0.68
    lar
    -0.67
    MJ
    -0.67
    tics
    -0.66
    ppo
    -0.63
     Pamela
    -0.63
     Occupations
    -0.63
    ORED
    -0.63
    POSITIVE LOGITS
    ments
    0.93
    ifty
    0.93
    initely
    0.88
    itude
    0.87
    ift
    0.87
    inho
    0.86
    itudes
    0.83
    ieth
    0.83
    withstanding
    0.82
    unction
    0.81
    Activations Density 0.073%

    No Known Activations