© 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. 11412
    Prev
    Next
    INDEX
    Explanations

    the term "outer" followed by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to "outer" layers or regions in various contexts

    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
    inatory
    -0.81
    anwhile
    -0.79
    inators
    -0.75
    inator
    -0.75
    utes
    -0.72
    inated
    -0.71
    ioned
    -0.67
    ammy
    -0.67
    âĵĺ
    -0.67
    inating
    -0.67
    POSITIVE LOGITS
    most
    1.30
    wear
    0.96
     casing
    0.92
     diameter
    0.90
    worldly
    0.87
    borough
    0.81
     lobe
    0.81
     garments
    0.80
     bounds
    0.78
     circumference
    0.78
    Activations Density 0.021%

    No Known Activations