© 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. 9-RES-JB
    11. 7306
    Prev
    Next
    INDEX
    Explanations

    words related to laws and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms that signify options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erest
    -0.76
    amines
    -0.75
    amine
    -0.70
    elsen
    -0.70
    poke
    -0.69
    ItemTracker
    -0.69
     Requirements
    -0.68
     Plans
    -0.67
     Principles
    -0.66
    ptives
    -0.66
    POSITIVE LOGITS
     otherwise
    1.53
    None
    0.75
    nam
    0.73
     extraord
    0.73
     nons
    0.72
     indifferent
    0.71
     unwitting
    0.66
     casual
    0.66
     unrem
    0.65
     none
    0.65
    Activations Density 0.126%

    No Known Activations