© 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. 3-RES-JB
    11. 12444
    Prev
    Next
    INDEX
    Explanations

    events or actions that happen simultaneously or correspondingly

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "coincide" and its variations, indicating relationships or associations between events or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agin
    -0.84
    chat
    -0.77
    verbs
    -0.71
    ilts
    -0.71
    cell
    -0.71
    liquid
    -0.67
    fat
    -0.64
    fing
    -0.64
    grass
    -0.64
    shit
    -0.63
    POSITIVE LOGITS
     coincide
    1.26
     coincides
    1.23
     coincided
    1.21
    uate
    0.92
    lihood
    0.80
     simultane
    0.80
    uates
    0.78
    rences
    0.77
    dayName
    0.73
     coinc
    0.73
    Activations Density 0.015%

    No Known Activations