© 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. 24103
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to notable figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals and organizations involved in speculation or potential future actions

    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
    ruciating
    -0.72
    phies
    -0.61
    _.
    -0.60
    Fill
    -0.59
    Reviewer
    -0.58
    assert
    -0.58
    Ô
    -0.57
    formance
    -0.55
     Parables
    -0.55
     noting
    -0.54
    POSITIVE LOGITS
     might
    1.31
     may
    1.24
    might
    1.10
     intends
    1.09
     originated
    1.04
     could
    0.99
     harb
    0.98
     faked
    0.97
     somehow
    0.96
     purposely
    0.96
    Activations Density 0.405%

    No Known Activations