© 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. 2248
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a need or requirement for action or resolution

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating necessity or unresolved issues

    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
    gdala
    -0.86
    deen
    -0.76
    azar
    -0.71
    SHIP
    -0.68
    ulty
    -0.67
    owship
    -0.62
    ILE
    -0.62
    ccording
    -0.62
    theless
    -0.61
    RANT
    -0.61
    POSITIVE LOGITS
    lessly
    1.06
     updating
    1.03
     tweaking
    1.02
     fixing
    0.97
     correcting
    0.96
     clarification
    0.93
     refinement
    0.92
     adjustment
    0.91
     adjusting
    0.90
     correction
    0.89
    Activations Density 0.047%

    No Known Activations