© 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. 10-RES-JB
    11. 12664
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs indicating uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    references to personal pronouns and their associated actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    venge
    -0.82
     Reverse
    -0.66
     fruition
    -0.61
     Allied
    -0.60
     mitigation
    -0.58
    coming
    -0.57
    GV
    -0.57
     Improvements
    -0.56
     culminating
    -0.56
    WARD
    -0.56
    POSITIVE LOGITS
     merely
    1.47
     simply
    1.25
     instead
    1.08
    Instead
    1.08
     only
    1.08
     just
    1.01
     Instead
    0.96
    only
    0.95
    Rather
    0.91
     certainly
    0.89
    Activations Density 0.347%

    No Known Activations