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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 13339
    Prev
    Next
    INDEX
    Explanations

    phrases related to a person named "Far" and potentially associated actions or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Far" or variations related to the character named Far

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uca
    -0.73
    rition
    -0.71
     elig
    -0.70
     crawl
    -0.69
     attrition
    -0.64
     starter
    -0.62
     beetle
    -0.61
    spr
    -0.61
    /?
    -0.60
    omatic
    -0.59
    POSITIVE LOGITS
     Far
    3.71
    Far
    2.59
     FAR
    1.83
    far
    1.81
     Near
    1.20
     Nay
    1.18
     far
    1.18
     Nor
    1.14
     Fah
    1.00
     Alt
    0.99
    Activations Density 0.013%

    No Known Activations