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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10-RES-JB
    6. 19154
    Prev
    Next
    INDEX
    Explanations

    technical information or product specifications expressed in the format "X/Y"

    oai_token-act-pair · gpt-3.5-turbo

    slash symbols and their variations in the text

    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
     soaring
    -0.74
     private
    -0.71
     speeches
    -0.71
     privately
    -0.70
     sooner
    -0.68
     pudding
    -0.68
     ost
    -0.67
     Kw
    -0.67
     elev
    -0.67
     Dw
    -0.66
    POSITIVE LOGITS
    1000
    1.30
    10
    1.18
    20
    1.17
    5
    1.17
    16
    1.15
    31
    1.14
    6000
    1.13
    365
    1.12
    oct
    1.12
    12
    1.11
    Activations Density 0.030%

    No Known Activations