© 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. 6-RES-JB
    11. 12896
    Prev
    Next
    INDEX
    Explanations

    the word "or" combined with context suggesting a role or function

    oai_token-act-pair · gpt-3.5-turbo

    terms related to roles or professions associated with overseeing, managing, or distributing goods or services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.77
    ilan
    -0.76
    schild
    -0.76
    imes
    -0.71
    illet
    -0.70
    imeo
    -0.63
    eneg
    -0.62
     Eater
    -0.60
     differe
    -0.59
     Liberties
    -0.59
    POSITIVE LOGITS
     thereof
    0.91
     beware
    0.82
     extraord
    0.82
    itative
    0.77
    ial
    0.74
    itatively
    0.74
    ship
    0.72
    agonist
    0.70
    operator
    0.70
    esses
    0.69
    Activations Density 0.121%

    No Known Activations