Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-RES-JB
    6. 18254
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions followed by verbs or nouns, often indicating actions or locations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in."

    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
     incumb
    -0.74
    llor
    -0.72
     endors
    -0.70
    cia
    -0.65
     defect
    -0.62
    rolet
    -0.62
    HAEL
    -0.62
    ML
    -0.61
    hirt
    -0.59
    killed
    -0.59
    POSITIVE LOGITS
     lieu
    1.21
     front
    1.20
     unison
    1.20
    animate
    1.15
    between
    1.13
     accordance
    1.12
     situ
    1.01
    escap
    1.01
    humane
    1.01
    organic
    1.00
    Activations Density 0.351%

    No Known Activations