© 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. 10-RES-JB
    11. 23505
    Prev
    Next
    INDEX
    Explanations

    verbs or adjectives related to intensity or energy

    oai_token-act-pair · gpt-3.5-turbo

    words related to various forms of contradiction or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moz
    -0.71
     Dahl
    -0.71
     Bridge
    -0.70
     Bever
    -0.69
     Waters
    -0.68
     Wast
    -0.66
     Insider
    -0.64
     Bridges
    -0.64
     Ferry
    -0.64
    Bey
    -0.63
    POSITIVE LOGITS
    eness
    0.96
    ophobic
    0.94
    atorial
    0.94
    iness
    0.94
    leness
    0.91
    acious
    0.89
    icultural
    0.87
    ularity
    0.87
    ification
    0.87
    ified
    0.87
    Activations Density 0.135%

    No Known Activations