Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16882
    Prev
    Next
    INDEX
    Explanations

    phrases related to going back or returning to a previous state or location

    oai_token-act-pair · gpt-3.5-turbo

    references to returning to a previous state or situation

    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
    yre
    -0.61
     Consent
    -0.60
    stood
    -0.60
    orst
    -0.57
    VICE
    -0.54
    anooga
    -0.54
    Merit
    -0.53
    Ire
    -0.52
    olulu
    -0.52
     Catch
    -0.51
    POSITIVE LOGITS
    packing
    1.16
    stab
    1.06
    tracking
    1.03
    gam
    0.99
    packs
    0.98
    track
    0.94
    doors
    0.89
    door
    0.89
    wards
    0.86
    stairs
    0.85
    Activations Density 0.028%

    No Known Activations