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. 13218
    Prev
    Next
    INDEX
    Explanations

    phrases describing the act of publicly criticizing or condemning someone or something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "call out."

    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
    olars
    -0.75
     gamble
    -0.72
    antry
    -0.68
     princip
    -0.65
     fall
    -0.63
    anos
    -0.63
     mint
    -0.60
    agan
    -0.59
     sleeve
    -0.59
    fing
    -0.59
    POSITIVE LOGITS
    stretched
    1.06
     loud
    0.92
    posts
    0.74
    worn
    0.71
    fitted
    0.71
     loudly
    0.68
    unci
    0.68
    STDOUT
    0.67
    wards
    0.67
    lier
    0.67
    Activations Density 0.017%

    No Known Activations