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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 9-RES-JB
    6. 18195
    Prev
    Next
    INDEX
    Explanations

    events or actions from the past

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "last" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lectic
    -0.64
    olor
    -0.61
    pherd
    -0.61
    leeve
    -0.57
    hetti
    -0.57
    cil
    -0.57
    death
    -0.57
    angan
    -0.56
     Hung
    -0.56
    waukee
    -0.55
    POSITIVE LOGITS
     week
    1.03
     year
    0.98
     rites
    0.90
     month
    0.87
     night
    0.87
     weekend
    0.87
    fm
    0.82
     yr
    0.79
     ditch
    0.79
     season
    0.76
    Activations Density 0.049%

    No Known Activations