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. 13255
    Prev
    Next
    INDEX
    Explanations

    references to specific names or terms related to reptiles and crocodiles

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Dwyane Wade and terms related to reptiles

    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
    espie
    -0.70
    IZE
    -0.68
     Mong
    -0.66
     Suffolk
    -0.66
     Sharif
    -0.64
     cigarettes
    -0.64
    corn
    -0.63
     Gillespie
    -0.63
     unpop
    -0.60
    chev
    -0.59
    POSITIVE LOGITS
     Dw
    0.89
    emer
    0.89
    itching
    0.88
    hist
    0.82
    ensional
    0.79
    orld
    0.79
    ngth
    0.76
    yers
    0.75
    itched
    0.75
    ör
    0.75
    Activations Density 0.045%

    No Known Activations