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. 14594
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences denoting a significant event or occurrence for the first time in a particular context

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "first time."

    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
    ouk
    -0.73
    otto
    -0.69
    Magic
    -0.69
    asty
    -0.65
    HEAD
    -0.63
    1950
    -0.63
    ourt
    -0.62
     $$
    -0.62
    better
    -0.61
    ead
    -0.61
    POSITIVE LOGITS
    soever
    0.85
     ever
    0.79
     lapse
    0.76
    ever
    0.73
     she
    0.69
     EVER
    0.69
    cia
    0.68
     anniversary
    0.67
     offenders
    0.65
    she
    0.63
    Activations Density 0.022%

    No Known Activations