© 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. 7473
    Prev
    Next
    INDEX
    Explanations

    specific locations or targets mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to location or locality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    child
    -0.90
    manship
    -0.80
    PDATE
    -0.80
    deen
    -0.73
     Duchess
    -0.68
    staking
    -0.66
    ħĭ
    -0.66
    uyomi
    -0.65
    thing
    -0.63
    FUL
    -0.62
    POSITIVE LOGITS
    abulary
    1.08
    atell
    1.05
    ator
    0.98
    ution
    0.95
    ocity
    0.95
    entric
    0.94
    ally
    0.91
    utor
    0.90
    aine
    0.90
    ators
    0.89
    Activations Density 0.033%

    No Known Activations