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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 2077
    Prev
    Next
    INDEX
    Explanations

    verbs related to stopping or restricting movement

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "grounded" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orr
    -0.84
    Article
    -0.74
    advertisement
    -0.74
    ocker
    -0.72
    opers
    -0.69
    apter
    -0.65
    oping
    -0.65
     MARK
    -0.65
    abet
    -0.65
     Means
    -0.64
    POSITIVE LOGITS
     grounded
    1.25
     grounding
    1.15
     anchored
    0.82
    rame
    0.80
     Zoro
    0.75
     anch
    0.73
     harmonic
    0.68
     adolesc
    0.67
    hog
    0.66
    zsche
    0.65
    Activations Density 0.003%

    No Known Activations