© 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. 2-RES-JB
    11. 17063
    Prev
    Next
    INDEX
    Explanations

    information or details that bring about surprise or a significant new understanding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant disclosures or surprises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    animate
    -0.79
    ucky
    -0.74
    osh
    -0.70
    chn
    -0.70
    resp
    -0.70
    cium
    -0.69
    cul
    -0.69
    acci
    -0.69
    veyard
    -0.68
    osuke
    -0.67
    POSITIVE LOGITS
     revelation
    1.27
     revelations
    1.27
     Revelations
    0.87
     reveals
    0.83
    Leaks
    0.82
     revealed
    0.81
     disclosures
    0.76
     aloud
    0.76
     reveal
    0.74
     loopholes
    0.71
    Activations Density 0.011%

    No Known Activations