© 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. 10-RES-JB
    11. 16411
    Prev
    Next
    INDEX
    Explanations

    phrases where a person gives a direct response or reply

    oai_token-act-pair · gpt-3.5-turbo

    instances of responses or replies in dialogue

    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
     ILCS
    -0.60
     Dracula
    -0.58
    enburg
    -0.57
    Pont
    -0.56
     foreseeable
    -0.56
    arta
    -0.55
     mutations
    -0.54
    illon
    -0.54
     Brotherhood
    -0.53
     vantage
    -0.53
    POSITIVE LOGITS
     sarcast
    1.12
     affirm
    1.02
     angrily
    1.01
     emphatically
    0.99
     bluntly
    0.97
    :"
    0.93
     enthusiastically
    0.91
     politely
    0.90
     yes
    0.88
     "@
    0.86
    Activations Density 0.083%

    No Known Activations