© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 241
    Prev
    Next
    INDEX
    Explanations

    instances of the term "common ground" in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "common ground" and the concept of gaining or losing ground in various contexts

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

    No Comments

    Negative Logits
    atto
    -0.65
    volent
    -0.63
     notor
    -0.62
    etics
    -0.62
    uras
    -0.61
    othy
    -0.61
    ansen
    -0.61
    ILA
    -0.60
    opes
    -0.60
    athetic
    -0.59
    POSITIVE LOGITS
     footing
    0.83
    cover
    0.79
    places
    0.78
    hog
    0.76
    ground
    0.75
    notes
    0.73
    floor
    0.73
    Ground
    0.72
     ground
    0.71
    wav
    0.69
    Activations Density 0.019%

    No Known Activations