© 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. 22593
    Prev
    Next
    INDEX
    Explanations

    lyric phrases related to track numbers

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions or references to sequels and continuations

    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
    awei
    -0.67
     bundles
    -0.64
    DH
    -0.63
    eneg
    -0.62
    sky
    -0.62
    horn
    -0.60
    voy
    -0.58
    leground
    -0.58
    rio
    -0.58
     Cosponsors
    -0.57
    POSITIVE LOGITS
     ensure
    0.97
    ggles
    0.95
     accompany
    0.93
     avoid
    0.90
     overcome
    0.90
     appease
    0.89
    wered
    0.86
     accommodate
    0.85
     minimize
    0.84
     explore
    0.84
    Activations Density 0.255%

    No Known Activations