© 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. 16248
    Prev
    Next
    INDEX
    Explanations

    places in a text where the phrase "at some point" is used

    oai_token-act-pair · gpt-3.5-turbo

    references to future events or moments in time

    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
    ords
    -0.73
    rats
    -0.70
    atts
    -0.69
    yet
    -0.69
    ctors
    -0.68
    LM
    -0.64
    atures
    -0.63
    GES
    -0.62
    velop
    -0.62
    rogens
    -0.62
    POSITIVE LOGITS
     during
    1.03
     throughout
    0.84
     thereafter
    0.73
     glance
    0.71
     midway
    0.71
     along
    0.70
    during
    0.69
     apiece
    0.68
     ago
    0.67
    point
    0.64
    Activations Density 0.048%

    No Known Activations