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. 18400
    Prev
    Next
    INDEX
    Explanations

    locations or directions referenced by the phrase "across the street"

    oai_token-act-pair · gpt-3.5-turbo

    references to locations with the phrase "across the street" or "around the corner."

    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
    Ô
    -0.76
    ĸļ
    -0.68
     pione
    -0.65
    acea
    -0.65
    imon
    -0.65
    cess
    -0.64
    isSpecial
    -0.64
    aution
    -0.62
    uckle
    -0.61
    ilyn
    -0.60
    POSITIVE LOGITS
     fence
    0.70
     sidx
    0.70
    yet
    0.65
    iffe
    0.64
    ilogy
    0.62
    waves
    0.61
     nexus
    0.61
    ulkan
    0.61
    uses
    0.60
    isphere
    0.60
    Activations Density 0.090%

    No Known Activations