© 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. 1-RES-JB
    11. 3120
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Spot" or related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Spot" and its variants in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cogn
    -0.73
    owan
    -0.73
    ĸļ
    -0.71
    orate
    -0.71
     oath
    -0.71
    aughter
    -0.70
    otype
    -0.70
    perty
    -0.68
     paternal
    -0.67
     mountainous
    -0.67
    POSITIVE LOGITS
    Spot
    1.54
     Spot
    1.11
    spot
    1.05
    bugs
    0.92
    lot
    0.90
    ãĤ§
    0.87
    atio
    0.84
    apter
    0.81
    pedia
    0.80
    ting
    0.80
    Activations Density 0.015%

    No Known Activations