© 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. 10-RES-JB
    11. 12850
    Prev
    Next
    INDEX
    Explanations

    repetitive actions or ongoing processes

    oai_token-act-pair · gpt-3.5-turbo

    repetitive forms of the verb "keep."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.93
    KEN
    -0.81
    iliary
    -0.74
    uably
    -0.73
    tainment
    -0.72
    inals
    -0.71
    izon
    -0.71
    issance
    -0.71
    assi
    -0.71
    ode
    -0.68
    POSITIVE LOGITS
     repeating
    1.18
     tabs
    1.16
     piling
    1.08
     insisting
    1.08
     pace
    1.07
     bothering
    1.07
     reminding
    1.07
     popping
    1.06
     pushing
    1.03
     slipping
    1.01
    Activations Density 0.036%

    No Known Activations