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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12581
    Prev
    Next
    INDEX
    Explanations

    commands and patterns related to coding and programming

    oai_token-act-pair · gpt-3.5-turbo

    references to administrative roles and related elements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ometimes
    -0.81
    etheless
    -0.75
     Cooke
    -0.69
     streng
    -0.64
     VIDEOS
    -0.63
    surprisingly
    -0.63
     interven
    -0.62
     Russo
    -0.61
     caut
    -0.60
    ansky
    -0.60
    POSITIVE LOGITS
    ")
    1.61
    "))
    1.56
    ").
    1.55
    ");
    1.49
    "]
    1.47
    "}
    1.45
    )",
    1.38
    )"
    1.32
    "),
    1.31
    ')
    1.31
    Activations Density 0.161%

    No Known Activations