© 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. 17358
    Prev
    Next
    INDEX
    Explanations

    words related to organized events or meetings

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "session"

    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
    umbai
    -0.63
    actor
    -0.62
    Vote
    -0.61
    hood
    -0.61
     Haram
    -0.61
    obal
    -0.59
     claws
    -0.58
    ":"/
    -0.58
    Lev
    -0.57
    ging
    -0.57
    POSITIVE LOGITS
     session
    1.04
    ional
    0.98
     sessions
    0.93
     Session
    0.83
    ansion
    0.80
     Minutes
    0.78
    ESSION
    0.78
    lain
    0.77
     Sessions
    0.76
     transcript
    0.74
    Activations Density 0.031%

    No Known Activations