© 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. 22471
    Prev
    Next
    INDEX
    Explanations

    phrases indicating surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express a lack of awareness or understanding

    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
    •layer 11 - surprise

    No Comments

    Negative Logits
    rend
    -0.80
    ugal
    -0.72
    cipl
    -0.70
    unity
    -0.66
    eous
    -0.66
     srfAttach
    -0.65
    pora
    -0.64
    only
    -0.64
    ror
    -0.62
    illed
    -0.61
    POSITIVE LOGITS
     remotely
    1.33
     bothering
    0.99
     bothered
    0.94
     vaguely
    0.93
     halfway
    0.90
     bother
    0.90
     hint
    0.85
     faintly
    0.84
     close
    0.84
     scratch
    0.83
    Activations Density 0.067%

    No Known Activations