© 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. 7-RES-JB
    11. 3139
    Prev
    Next
    INDEX
    Explanations

    places or topics of discussion related to decision-making or controversy

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eworks
    -0.79
    vironments
    -0.69
    ses
    -0.68
     Antiqu
    -0.67
    eus
    -0.66
     Pants
    -0.64
     Elements
    -0.64
     subtitles
    -0.63
    azines
    -0.62
    gements
    -0.61
    POSITIVE LOGITS
     unto
    0.93
     worthy
    0.84
     breaker
    0.76
     impossibility
    0.75
    starter
    0.75
    breaker
    0.74
     staple
    0.72
     reminder
    0.70
    less
    0.70
    inel
    0.69
    Activations Density 0.249%

    No Known Activations