© 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. 11-RES-JB
    11. 7059
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a call to action or a need for intervention

    oai_token-act-pair · gpt-3.5-turbo

    verbs indicating obligations or actions that should be taken

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.69
     favoured
    -0.69
    icipated
    -0.66
    anka
    -0.63
     unlucky
    -0.63
    ulty
    -0.63
    anticipated
    -0.62
     combinations
    -0.62
     favourable
    -0.62
     fav
    -0.62
    POSITIVE LOGITS
     apologize
    1.22
     STOP
    1.20
     repent
    1.15
     realize
    1.13
     stop
    1.10
     cease
    1.10
     rethink
    1.08
     denounce
    1.07
     apologise
    1.05
     disav
    1.03
    Activations Density 0.368%

    No Known Activations