© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 11705
    Prev
    Next
    INDEX
    Explanations

    phrases related to completion or fulfillment

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "one" and variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     induct
    -0.74
     wid
    -0.62
     spir
    -0.61
     ev
    -0.59
     instruct
    -0.59
     Revel
    -0.59
     Erd
    -0.58
     Geral
    -0.58
     dow
    -0.58
     reg
    -0.58
    POSITIVE LOGITS
    ONE
    4.25
    ONES
    2.67
    THING
    1.97
    WHERE
    1.67
    ones
    1.66
    ODY
    1.63
    one
    1.49
     ONE
    1.44
    ONY
    1.43
    ERO
    1.40
    Activations Density 0.019%

    No Known Activations