© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10261
    Prev
    Next
    INDEX
    Explanations

    references to actions perceived as negative or harmful to others

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or shock regarding human actions or events

    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
     Occasionally
    -0.64
     periodically
    -0.58
     shortly
    -0.55
     endif
    -0.54
    Newsletter
    -0.54
     assures
    -0.54
     explains
    -0.53
     respectively
    -0.52
     incumb
    -0.51
     summarizes
    -0.51
    POSITIVE LOGITS
     such
    1.30
    such
    1.12
    Such
    0.97
     anything
    0.96
     this
    0.93
     Such
    0.93
    this
    0.92
     THIS
    0.92
    these
    0.87
     THAT
    0.85
    Activations Density 0.564%

    No Known Activations