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. 6-RES-JB
    6. 1798
    Prev
    Next
    INDEX
    Explanations

    instances where the document states that something has not yet occurred

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "not yet."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rities
    -0.82
    sym
    -0.75
    pmwiki
    -0.72
    gencies
    -0.70
    lav
    -0.70
    ãĥ¼ãĥĨãĤ£
    -0.68
    Pers
    -0.68
    harm
    -0.68
    mut
    -0.67
    regate
    -0.67
    POSITIVE LOGITS
     finalized
    0.91
     officially
    0.90
     formally
    0.89
     anymore
    0.89
     mastered
    0.86
     finished
    0.85
    hin
    0.82
     fulfilled
    0.81
     understood
    0.80
    icable
    0.80
    Activations Density 0.017%

    No Known Activations