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. 8974
    Prev
    Next
    INDEX
    Explanations

    dialogue exchanges including characters' names and actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express enthusiasm or excitement

    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
     batters
    -0.72
     Semin
    -0.71
     NCT
    -0.68
    utm
    -0.66
    Posted
    -0.66
     Zamb
    -0.63
    geoning
    -0.63
     subp
    -0.63
     innov
    -0.62
    imeo
    -0.62
    POSITIVE LOGITS
    -"
    1.35
    â̦"
    1.11
    —"
    1.08
    ..."
    1.06
    ãĢı
    0.98
     Mistress
    0.95
     â̦"
    0.94
    !?"
    0.92
    â̦."
    0.90
     Hogwarts
    0.88
    Activations Density 0.403%

    No Known Activations