© 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. 9242
    Prev
    Next
    INDEX
    Explanations

    references to the character "Pyrrha" and some related entities

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns and names of characters

    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
    Indiana
    -0.85
    tery
    -0.82
    draw
    -0.74
    ktop
    -0.74
    $$$$
    -0.72
    creen
    -0.72
    aton
    -0.69
    milo
    -0.69
    DT
    -0.69
    score
    -0.68
    POSITIVE LOGITS
     Grimm
    1.17
     RW
    0.90
     Beacon
    0.85
     Arc
    0.80
     Weaver
    0.77
     Pyrrha
    0.75
     Cascade
    0.75
     semblance
    0.74
     Oz
    0.73
     Emerald
    0.72
    Activations Density 0.018%

    No Known Activations