© 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. 11-RES-JB
    11. 9919
    Prev
    Next
    INDEX
    Explanations

    seasons and specific times of year mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to seasons and times of day

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edIn
    -0.71
     Gleaming
    -0.63
    ophy
    -0.60
     predec
    -0.60
    enf
    -0.59
    fam
    -0.58
     Inher
    -0.57
    ¶æ
    -0.56
     cous
    -0.56
    ailable
    -0.55
    POSITIVE LOGITS
    osphere
    0.98
     timeframe
    0.86
     realm
    0.83
     era
    0.79
     aisle
    0.78
    liest
    0.78
     area
    0.77
     months
    0.76
    imester
    0.75
     phase
    0.75
    Activations Density 0.270%

    No Known Activations