© 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. 4056
    Prev
    Next
    INDEX
    Explanations

    words related to causation, specifically actions leading to certain outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "lead" and its variations related to consequences or effects

    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
    osal
    -0.57
    atching
    -0.56
    ighth
    -0.55
    done
    -0.54
    iling
    -0.53
     Speaking
    -0.52
    uesday
    -0.51
    ature
    -0.50
    _>
    -0.50
    _-_
    -0.50
    POSITIVE LOGITS
     to
    1.09
     inevitably
    0.95
     nowhere
    0.93
     inex
    0.93
     directly
    0.89
     toward
    0.84
     towards
    0.79
     us
    0.77
    entious
    0.76
     into
    0.73
    Activations Density 0.080%

    No Known Activations