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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 16725
    Prev
    Next
    INDEX
    Explanations

    official website names and launch dates

    oai_token-act-pair · gpt-3.5-turbo

    official website references and site-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     printer
    -0.73
     recl
    -0.73
     printers
    -0.70
    pi
    -0.69
     eyeb
    -0.69
     conscientious
    -0.68
     licens
    -0.67
     vacc
    -0.66
    clus
    -0.64
     spac
    -0.64
    POSITIVE LOGITS
     Begins
    0.91
     TBA
    0.89
     Coming
    0.75
     Includes
    0.75
     Provider
    0.74
     Goes
    0.73
    urations
    0.73
     Extras
    0.71
     Detected
    0.70
    URN
    0.70
    Activations Density 0.188%

    No Known Activations