© 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. 8-RES-JB
    11. 18671
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and expressions related to personal attributes

    oai_token-act-pair · gpt-3.5-turbo

    references to age and youth-related themes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Information
    -0.75
     notification
    -0.74
     confidentiality
    -0.73
     reimbursement
    -0.71
     Priority
    -0.69
    Amount
    -0.66
    Prior
    -0.66
     certification
    -0.66
    ource
    -0.64
    Statement
    -0.64
    POSITIVE LOGITS
     perched
    0.83
     gripped
    0.81
     gorge
    0.80
     mesmer
    0.79
     frontman
    0.74
     plung
    0.74
     dazz
    0.74
     capt
    0.73
     indul
    0.72
     plunged
    0.71
    Activations Density 0.924%

    No Known Activations