© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23224
    Prev
    Next
    INDEX
    Explanations

    phrases related to contemplation and questioning

    oai_token-act-pair · gpt-3.5-turbo

    expressions of uncertainty or questioning statements

    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
    isle
    -0.59
    catentry
    -0.57
    haw
    -0.56
    aci
    -0.55
     ASAP
    -0.54
     eyeb
    -0.53
     testers
    -0.53
     rundown
    -0.53
     ROCK
    -0.52
     Tackle
    -0.52
    POSITIVE LOGITS
     ever
    1.68
     imaginable
    1.57
     conceivable
    1.49
    ever
    1.48
     EVER
    1.46
    soever
    1.17
     slightest
    1.13
     anywhere
    1.13
     anyone
    1.11
     dare
    1.09
    Activations Density 0.468%

    No Known Activations