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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 17306
    Prev
    Next
    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "here" and its variations, highlighting a focus on location or presence

    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
    inventoryQuantity
    -0.67
     Decay
    -0.61
    mble
    -0.59
    ahime
    -0.59
     Panzer
    -0.58
    catentry
    -0.58
     Thrones
    -0.57
    IRC
    -0.56
     Holt
    -0.56
    Edge
    -0.54
    POSITIVE LOGITS
    tics
    1.84
    tical
    1.77
    abouts
    1.63
    tic
    1.45
    to
    0.90
    with
    0.88
     illegally
    0.78
    after
    0.74
    upon
    0.72
    ground
    0.70
    Activations Density 0.055%

    No Known Activations