© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2206
    Prev
    Next
    INDEX
    Explanations

    phrases indicating movement or progression in a temporal context

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to progress or direction towards a future event or state

    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
    eness
    -0.59
    licks
    -0.59
    ATA
    -0.57
    erest
    -0.56
    trak
    -0.55
    ules
    -0.55
     Oops
    -0.54
     DISTR
    -0.54
    awi
    -0.54
    OUP
    -0.53
    POSITIVE LOGITS
     into
    1.14
     forward
    1.05
    into
    1.02
    forward
    0.95
     INTO
    0.95
     Into
    0.83
     onward
    0.83
     onwards
    0.79
     forwards
    0.77
     onto
    0.75
    Activations Density 0.123%

    No Known Activations