© 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. 22502
    Prev
    Next
    INDEX
    Explanations

    pronouns and verbs related to self-identity

    oai_token-act-pair · gpt-3.5-turbo

    references to identity and self-perception

    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
    artifacts
    -0.62
     diffusion
    -0.61
     Grounds
    -0.60
     liner
    -0.60
    hill
    -0.59
     Passage
    -0.57
     horizont
    -0.57
    UCT
    -0.56
     sheds
    -0.55
     adv
    -0.55
    POSITIVE LOGITS
    borgh
    0.76
     become
    0.72
     am
    0.71
    uably
    0.70
    Thumbnail
    0.68
     Become
    0.66
     truly
    0.66
    ãĤ«
    0.63
     pretended
    0.62
     aspire
    0.62
    Activations Density 0.117%

    No Known Activations