© 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. 9421
    Prev
    Next
    INDEX
    Explanations

    the word "endless"

    oai_token-act-pair · gpt-3.5-turbo

    iterations of the word "endless."

    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
    acus
    -0.80
    illard
    -0.78
    PI
    -0.75
    BU
    -0.72
    istics
    -0.72
    ained
    -0.71
    Reviewed
    -0.71
    ribution
    -0.69
    oral
    -0.68
     Taken
    -0.68
    POSITIVE LOGITS
     endless
    0.89
     repetition
    0.89
    etheless
    0.79
     repet
    0.75
    urous
    0.74
     expans
    0.74
     plains
    0.73
     gratification
    0.73
     replay
    0.72
     tort
    0.72
    Activations Density 0.010%

    No Known Activations