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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 16900
    Prev
    Next
    INDEX
    Explanations

    mentions of current events or recent trends

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a fresh start or new opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     evolves
    -0.61
    antis
    -0.60
     progresses
    -0.58
    atories
    -0.57
    ulative
    -0.57
    erial
    -0.57
    lasting
    -0.54
     grows
    -0.53
     asymm
    -0.53
    UTC
    -0.53
    POSITIVE LOGITS
     congratulations
    0.74
     probably
    0.73
    NOW
    0.73
    starter
    0.70
     rejoice
    0.70
    joy
    0.70
    your
    0.69
     RELE
    0.68
    prime
    0.67
     surely
    0.67
    Activations Density 0.223%

    No Known Activations