© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8-RES-JB
    11. 14469
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "Before" indicating a temporal context or narrative sequence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    geist
    -0.79
    aren
    -0.73
    ILY
    -0.69
    VERTISEMENT
    -0.68
    among
    -0.66
    ARS
    -0.65
    atically
    -0.64
    aternity
    -0.64
    atic
    -0.62
    tap
    -0.61
    POSITIVE LOGITS
    hand
    0.82
    cluding
    0.82
     embark
    0.79
    rely
    0.76
     concluding
    0.74
     retiring
    0.72
    empt
    0.69
    noon
    0.69
     closing
    0.68
     departing
    0.68
    Activations Density 0.033%

    No Known Activations