© 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. 18826
    Prev
    Next
    INDEX
    Explanations

    positive adverbs indicating success or effectiveness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "well" indicating positive performance or effectiveness

    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
    ility
    -0.70
    agine
    -0.66
    owners
    -0.65
    ilities
    -0.62
    ropy
    -0.62
     Disability
    -0.60
    anasia
    -0.60
    anish
    -0.59
    rush
    -0.59
    rification
    -0.59
    POSITIVE LOGITS
     enough
    1.37
    enough
    1.18
     Enough
    0.96
     suited
    0.84
     behaved
    0.79
    spring
    0.79
    bye
    0.77
     together
    0.75
     indeed
    0.73
    baum
    0.71
    Activations Density 0.072%

    No Known Activations