© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 11375
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating significant first occurrences or historical milestones

    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
    rien
    -0.63
    Max
    -0.63
    ned
    -0.62
    mel
    -0.60
    peer
    -0.58
    ibr
    -0.58
    mosp
    -0.58
    Progress
    -0.57
    anism
    -0.56
    isa
    -0.55
    POSITIVE LOGITS
     sake
    1.33
     purposes
    1.13
     reasons
    1.00
     eternity
    0.94
    ummies
    0.80
     indefinite
    0.78
    instance
    0.76
     purpose
    0.75
     duration
    0.73
    ocument
    0.72
    Activations Density 0.105%

    No Known Activations