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. 0-RES-JB
    6. 3260
    Prev
    Next
    INDEX
    Explanations

    words related to physical surfaces or locations such as "ground" or "floor."

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "ground" and its contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assist
    -0.67
    SHARE
    -0.64
    omnia
    -0.63
    Writer
    -0.62
    asks
    -0.61
    Quote
    -0.61
    watch
    -0.61
    nia
    -0.61
    FILE
    -0.60
    justice
    -0.60
    POSITIVE LOGITS
     ground
    4.06
     Ground
    2.79
    ground
    2.72
    Ground
    2.63
     grounds
    1.88
     Grounds
    1.63
     grounding
    1.39
     soil
    1.39
     turf
    1.37
     terrain
    1.31
    Activations Density 0.016%

    No Known Activations