© 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. 3063
    Prev
    Next
    INDEX
    Explanations

    phrases related to different types of occupations or professions that involve working

    oai_token-act-pair · gpt-3.5-turbo

    job titles or roles referenced in the text

    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
    TPPStreamerBot
    -0.72
    ãĥīãĥ©
    -0.65
     suscept
    -0.64
     Ambro
    -0.63
    éŃĶ
    -0.62
    Inv
    -0.61
    NetMessage
    -0.61
    threat
    -0.61
    lege
    -0.60
     snapshots
    -0.60
    POSITIVE LOGITS
    ework
    0.83
    ournal
    0.79
    hops
    0.74
     tirelessly
    0.69
     shifts
    0.68
     fronts
    0.68
    enhagen
    0.67
     collabor
    0.67
    chemy
    0.65
    ça
    0.64
    Activations Density 0.182%

    No Known Activations