© 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. 12257
    Prev
    Next
    INDEX
    Explanations

    personal experiences or opinions expressed by someone

    oai_token-act-pair · gpt-3.5-turbo

    first-person expressions of personal experiences and feelings

    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
    gravity
    -0.55
    redients
    -0.53
    inks
    -0.53
     Gibbs
    -0.51
    advertisement
    -0.51
    interstitial
    -0.50
     gist
    -0.49
     predomin
    -0.49
    ibility
    -0.49
     Phi
    -0.48
    POSITIVE LOGITS
     ever
    1.54
     EVER
    1.40
    ever
    1.17
     Ever
    1.06
    Ever
    1.02
    've
    1.01
     imaginable
    0.98
     encountered
    0.96
     encount
    0.87
    'd
    0.87
    Activations Density 0.077%

    No Known Activations