© 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. 16340
    Prev
    Next
    INDEX
    Explanations

    phrases related to continual change or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating continuous or repetitive actions

    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
    omsky
    -0.81
    jl
    -0.73
    lda
    -0.73
    hemy
    -0.69
    IDA
    -0.68
    gemony
    -0.68
    DIT
    -0.67
    pta
    -0.67
    elson
    -0.67
    AMI
    -0.67
    POSITIVE LOGITS
     evolving
    1.05
     updating
    1.04
     changing
    0.98
     replen
    0.98
     shifting
    0.98
     reminding
    0.96
     reinvent
    0.96
     refreshed
    0.94
     striving
    0.93
     churn
    0.91
    Activations Density 0.062%

    No Known Activations