© 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. 5317
    Prev
    Next
    INDEX
    Explanations

    mentions of ownership and affiliation

    oai_token-act-pair · gpt-3.5-turbo

    a repeated phrase that expresses agreement or affirmation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Bagg
    -0.61
     pots
    -0.60
     itiner
    -0.59
     resorts
    -0.56
     schedules
    -0.55
    bies
    -0.54
     resort
    -0.54
     lay
    -0.54
     subcontract
    -0.53
     satellite
    -0.53
    POSITIVE LOGITS
    aurus
    0.85
    wered
    0.85
    worth
    0.84
    oda
    0.84
    mean
    0.84
     gonna
    0.84
    ELF
    0.81
    lightly
    0.79
    forth
    0.78
    ï¸
    0.77
    Activations Density 0.043%

    No Known Activations