© 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. 0-RES-JB
    11. 1292
    Prev
    Next
    INDEX
    Explanations

    strings related to "Pokémon" with different variations and contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to Pokémon

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTAL
    -0.79
    othy
    -0.75
    acus
    -0.73
    >)
    -0.71
    roying
    -0.70
    akespe
    -0.70
    \/\/
    -0.68
     Buckley
    -0.66
    idia
    -0.65
     Seym
    -0.64
    POSITIVE LOGITS
     and
    0.80
     with
    0.72
    âĵĺ
    0.71
     coaster
    0.63
     knife
    0.59
    anded
    0.58
    andowski
    0.57
     Kag
    0.56
     sten
    0.56
    kt
    0.56
    Activations Density 0.000%

    No Known Activations