© 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. 12104
    Prev
    Next
    INDEX
    Explanations

    phrases related to extended periods of time

    oai_token-act-pair · gpt-3.5-turbo
    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
     Compass
    -0.74
    Cu
    -0.74
    IRO
    -0.72
    ĪĴ
    -0.67
     NTS
    -0.65
     Offic
    -0.64
     Avenger
    -0.63
    leck
    -0.62
    psy
    -0.62
    Tro
    -0.61
    POSITIVE LOGITS
     periods
    1.57
    term
    1.37
    itud
    1.34
     term
    1.25
    lasting
    1.21
     distances
    1.18
     stretches
    1.16
     duration
    1.13
    itudes
    1.11
    itudinal
    1.06
    Activations Density 0.067%

    No Known Activations