© 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. 17145
    Prev
    Next
    INDEX
    Explanations

    conditional statements

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and hypotheses related to scenarios or rules

    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
    çīĪ
    -0.71
    ãĤ´ãĥ³
    -0.69
    undo
    -0.68
    çļĦ
    -0.64
    ++;
    -0.63
    hig
    -0.62
    ãĥ³ãĤ¸
    -0.61
    çİĭ
    -0.60
    minus
    -0.60
    odon
    -0.59
    POSITIVE LOGITS
     someone
    1.35
     you
    1.32
     somebody
    1.30
    someone
    1.10
     your
    1.02
     something
    0.93
    you
    0.90
     YOU
    0.87
     we
    0.87
     an
    0.84
    Activations Density 0.291%

    No Known Activations