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. 22994
    Prev
    Next
    INDEX
    Explanations

    phrases tagged with "/**9" which seem to be related to requests or urgent situations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of asterisks or bullet points in the text

    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
    ly
    -0.81
    liness
    -0.75
     dispers
    -0.69
    liest
    -0.67
    ijk
    -0.67
    iop
    -0.65
    ilia
    -0.65
    ilic
    -0.64
    aea
    -0.63
     relocation
    -0.62
    POSITIVE LOGITS
    kw
    1.03
    hole
    0.83
    Edited
    0.79
    THIS
    0.79
    orks
    0.78
    Discussion
    0.77
    Madison
    0.77
    DOWN
    0.75
    ski
    0.74
    WARNING
    0.74
    Activations Density 0.016%

    No Known Activations