© 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. 6-RES-JB
    11. 18443
    Prev
    Next
    INDEX
    Explanations

    words related to scheduling or planning

    oai_token-act-pair · gpt-3.5-turbo

    words related to scheming or plotting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Advocate
    -0.70
     baptism
    -0.68
     Canterbury
    -0.66
     justice
    -0.63
     Rabb
    -0.62
     Isles
    -0.62
     Royale
    -0.61
     duty
    -0.61
     Patt
    -0.61
     kindness
    -0.59
    POSITIVE LOGITS
    ming
    1.18
    dule
    1.17
    stal
    1.06
    etary
    1.05
    mers
    0.99
    mes
    0.97
    py
    0.92
    enei
    0.91
    ateg
    0.90
    schild
    0.89
    Activations Density 0.058%

    No Known Activations