© 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. 1677
    Prev
    Next
    INDEX
    Explanations

    actions that haven't been fully completed or decided upon yet

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating actions that have not yet occurred or have been unresolved

    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
    odge
    -0.67
     shalt
    -0.59
     Hait
    -0.58
    uez
    -0.57
    igi
    -0.54
    otti
    -0.54
    instead
    -0.52
    abet
    -0.52
    oir
    -0.51
     unwitting
    -0.51
    POSITIVE LOGITS
     yet
    2.51
    yet
    2.41
     Yet
    1.49
     nor
    1.26
     lately
    1.21
    Yet
    1.17
     anymore
    1.13
    nor
    1.04
     already
    1.02
    enough
    0.96
    Activations Density 0.568%

    No Known Activations