Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 17057
    Prev
    Next
    INDEX
    Explanations

    verbs related to the passage of time, sequences of events, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    instances of decision-making or announcements following a deliberation process

    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
    EY
    -0.70
    PI
    -0.67
    JV
    -0.66
    SOURCE
    -0.66
    kin
    -0.64
    role
    -0.63
    gard
    -0.62
    ahar
    -0.62
    MW
    -0.61
    DN
    -0.61
    POSITIVE LOGITS
     finally
    1.00
     culminating
    0.83
    icably
    0.80
     settled
    0.78
     eventually
    0.78
     resur
    0.77
     abruptly
    0.76
     concluding
    0.73
     settling
    0.72
     decided
    0.70
    Activations Density 0.211%

    No Known Activations