© 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. 4-RES-JB
    11. 3693
    Prev
    Next
    INDEX
    Explanations

    warnings or cautionary statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "warned."

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

    No Comments

    Negative Logits
    EMS
    -0.74
    animate
    -0.73
    á
    -0.67
    NAS
    -0.67
    Interstitial
    -0.66
    anuts
    -0.65
    Boot
    -0.65
    dx
    -0.64
    rafted
    -0.63
    PB
    -0.63
    POSITIVE LOGITS
    warn
    1.01
     omin
    0.94
     Warn
    0.91
    warning
    0.91
     warnings
    0.89
     warns
    0.87
     warn
    0.82
     warning
    0.82
     warned
    0.81
     repeatedly
    0.76
    Activations Density 0.017%

    No Known Activations