© 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. 24060
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or confidence

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing certainty or assurance

    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
    ublic
    -0.70
     contrace
    -0.66
    inese
    -0.66
     concurrently
    -0.62
    pmwiki
    -0.61
    ynchron
    -0.59
    èĢħ
    -0.59
     Combine
    -0.59
     Peninsula
    -0.57
    poral
    -0.55
    POSITIVE LOGITS
    footed
    1.40
    fire
    1.22
    ty
    1.10
    ndra
    0.87
     Gamble
    0.86
    tta
    0.86
    gard
    0.85
    ties
    0.85
     enough
    0.75
    tale
    0.74
    Activations Density 0.043%

    No Known Activations