© 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. 22661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating uncertainty or lack of clarity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "at this point" in the text

    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
     Virtue
    -0.66
    forcement
    -0.60
     Protect
    -0.59
    icons
    -0.59
    ãĥĻ
    -0.59
     Sections
    -0.58
    Compat
    -0.57
    errors
    -0.57
     rolls
    -0.57
    packages
    -0.57
    POSITIVE LOGITS
     point
    1.47
     jun
    1.44
     moment
    1.31
     stage
    1.30
     time
    1.13
    point
    1.10
     rate
    1.00
     junction
    0.97
     pace
    0.96
     hour
    0.92
    Activations Density 0.032%

    No Known Activations