© 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. 15005
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "directly" in relation to other entities or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directly" and its context within sentences

    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
    gerald
    -0.95
    glers
    -0.73
    ifully
    -0.69
    ulton
    -0.66
     Scor
    -0.66
     cautiously
    -0.63
    ĸļ
    -0.63
    eland
    -0.63
     Garry
    -0.62
     stal
    -0.62
    POSITIVE LOGITS
     contradicted
    0.85
     contradicts
    0.77
     addressed
    0.77
     benefited
    0.77
     identifiable
    0.75
    forward
    0.74
    ebted
    0.73
     contradict
    0.73
     attributable
    0.72
     impacted
    0.70
    Activations Density 0.025%

    No Known Activations