© 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. 11-RES-JB
    11. 19306
    Prev
    Next
    INDEX
    Explanations

    financial figures and statistics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "for" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    edin
    -0.72
    angelo
    -0.67
    orbit
    -0.64
    Join
    -0.63
     gladly
    -0.63
    heid
    -0.62
    hess
    -0.62
    halla
    -0.62
    Fight
    -0.61
    hack
    -0.61
    POSITIVE LOGITS
    geries
    1.17
     purposes
    1.14
     each
    1.12
     every
    1.07
     instance
    1.04
     example
    1.02
     starters
    0.98
    going
    0.97
    gery
    0.96
     comparison
    0.92
    Activations Density 0.140%

    No Known Activations