© 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. 2-RES-JB
    11. 4417
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'Spotlight'

    oai_token-act-pair · gpt-3.5-turbo

    references to "Spot" and variations of it, likely relating to a particular subject or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.96
    otype
    -0.73
    velt
    -0.70
     detached
    -0.69
    aughter
    -0.68
     ransom
    -0.65
     shroud
    -0.65
     havoc
    -0.64
     fullest
    -0.64
    perty
    -0.64
    POSITIVE LOGITS
    Spot
    1.34
     Spot
    1.03
    ting
    0.98
    spot
    0.95
    lot
    0.91
    atio
    0.85
    lights
    0.82
    apter
    0.82
    ãĤ§
    0.81
    light
    0.81
    Activations Density 0.013%

    No Known Activations