© 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. 10-RES-JB
    11. 20228
    Prev
    Next
    INDEX
    Explanations

    comparisons or contrasts between different situations or entities

    oai_token-act-pair · gpt-3.5-turbo

    situations that contrast expectations versus reality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -0.76
     actionGroup
    -0.73
     Viol
    -0.62
    istics
    -0.62
     guiActiveUnfocused
    -0.62
     ACTIONS
    -0.61
     ZIP
    -0.60
     Leilan
    -0.60
    ario
    -0.60
     Absent
    -0.59
    POSITIVE LOGITS
     feared
    1.11
     claimed
    1.10
     hoped
    1.08
     imagined
    1.03
     advertised
    1.00
     assumed
    0.98
     portrayed
    0.94
     implied
    0.93
     predicted
    0.93
     anticipated
    0.92
    Activations Density 0.195%

    No Known Activations