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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 23289
    Prev
    Next
    INDEX
    Explanations

    the word "front" in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "in front."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cci
    -0.92
    zie
    -0.82
    IRO
    -0.75
    Rating
    -0.73
    assets
    -0.73
    chini
    -0.72
     Flavoring
    -0.71
    vil
    -0.70
    cano
    -0.70
    ARP
    -0.70
    POSITIVE LOGITS
     facing
    0.74
    ed
    0.74
     row
    0.71
     teeth
    0.70
    eering
    0.67
    runners
    0.66
    ocrin
    0.66
    office
    0.66
    sburg
    0.65
     yard
    0.65
    Activations Density 0.010%

    No Known Activations