© 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. 3-RES-JB
    11. 1706
    Prev
    Next
    INDEX
    Explanations

    keywords related to entities or objects mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to additional groups or entities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     2024
    -0.75
    ffee
    -0.69
     1915
    -0.69
     1962
    -0.66
     Lent
    -0.64
     Tanaka
    -0.64
    assis
    -0.63
     1963
    -0.62
     Kubrick
    -0.62
     1961
    -0.61
    POSITIVE LOGITS
    worldly
    1.57
     assorted
    0.89
     kinds
    0.83
    wise
    0.83
     types
    0.82
     aspects
    0.82
     countries
    0.80
    etheless
    0.80
     kindred
    0.79
     avenues
    0.78
    Activations Density 0.087%

    No Known Activations