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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    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. 6-RES-JB
    6. 14306
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical programming concepts and code

    oai_token-act-pair · gpt-3.5-turbo

    specific structural elements and references within coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     darts
    -0.70
    sight
    -0.67
     conduc
    -0.66
     seiz
    -0.65
    afety
    -0.60
     straps
    -0.60
     seams
    -0.59
     calves
    -0.58
     ropes
    -0.58
     Slater
    -0.56
    POSITIVE LOGITS
    ļéĨĴ
    0.97
    aeper
    0.78
    BuyableInstoreAndOnline
    0.70
    itol
    0.68
    ñ
    0.67
     Ibid
    0.67
     BaseType
    0.65
    ò
    0.64
    Þ
    0.63
    TextColor
    0.62
    Activations Density 0.382%

    No Known Activations