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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 9-RES-JB
    6. 16977
    Prev
    Next
    INDEX
    Explanations

    texts with citation formats

    oai_token-act-pair · gpt-3.5-turbo

    numerical references and publication details in academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wed
    -0.81
     unlucky
    -0.78
     NXT
    -0.75
     lucky
    -0.74
     riding
    -0.72
     decor
    -0.71
     rooting
    -0.71
     inexper
    -0.71
    manship
    -0.70
     friendly
    -0.70
    POSITIVE LOGITS
    âĵĺ
    1.39
     Ibid
    1.33
    http
    1.25
    Abstract
    1.11
    Reviewer
    1.09
    References
    1.08
    doi
    1.07
     Retrieved
    1.04
     doi
    1.01
    https
    1.01
    Activations Density 0.214%

    No Known Activations