© 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. 17263
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical abilities or qualities related to strength, agility, speed, and reflexes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to physical attributes and actions, particularly focusing on reflexes and expansive concepts

    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
    izoph
    -0.67
     Peninsula
    -0.66
     rh
    -0.63
     damn
    -0.61
     Harbour
    -0.61
     dear
    -0.59
     shore
    -0.58
    udder
    -0.57
     supervised
    -0.57
     Psychiatry
    -0.56
    POSITIVE LOGITS
    es
    2.87
    ively
    1.56
    ed
    1.55
    esville
    1.40
    ions
    1.36
    esy
    1.32
    esian
    1.24
    eson
    1.24
    ES
    1.23
    edly
    1.20
    Activations Density 0.222%

    No Known Activations