© 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. 1-RES-JB
    11. 13365
    Prev
    Next
    INDEX
    Explanations

    phrases related to actions or events that have occurred or been completed

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "been" indicating ongoing actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eers
    -0.78
    rones
    -0.73
    regate
    -0.68
    izes
    -0.64
    odder
    -0.63
     Hole
    -0.62
     Hou
    -0.60
    Guy
    -0.60
    rates
    -0.59
    arms
    -0.59
    POSITIVE LOGITS
     seen
    0.93
     able
    0.93
     bitten
    0.91
     taken
    0.85
     shown
    0.83
     given
    0.80
     done
    0.80
     eaten
    0.78
     consulted
    0.77
     born
    0.77
    Activations Density 0.122%

    No Known Activations