© 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. 7746
    Prev
    Next
    INDEX
    Explanations

    mentions of teamwork and collaboration

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing frustration

    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
     confiscated
    -0.71
     reported
    -0.68
     seized
    -0.67
     completed
    -0.66
     retrieved
    -0.66
     resumed
    -0.65
     duly
    -0.65
     promptly
    -0.65
     restored
    -0.64
     barred
    -0.64
    POSITIVE LOGITS
     yeah
    1.17
    laughs
    1.15
    Yeah
    1.08
     somebody
    1.05
    Whereas
    1.02
     secondly
    1.00
    you
    0.98
    Especially
    0.98
    Sometimes
    0.97
    entimes
    0.97
    Activations Density 0.593%

    No Known Activations