© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 12686
    Prev
    Next
    INDEX
    Explanations

    terms related to helpfulness and providing assistance, particularly directed towards newcomers

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a focus on helping newcomers to a particular activity or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĵĺ
    -0.75
     incorpor
    -0.73
    omore
    -0.72
     suspend
    -0.71
     correctness
    -0.70
     satell
    -0.66
    =#
    -0.65
     hiatus
    -0.63
    zbollah
    -0.63
    etheless
    -0.63
    POSITIVE LOGITS
     Yar
    0.66
    edia
    0.66
     Anth
    0.66
     Vit
    0.64
     nas
    0.64
     Gamer
    0.64
    dit
    0.64
     Crit
    0.62
    ronic
    0.62
    Wiki
    0.62
    Activations Density 0.000%

    No Known Activations