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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4293
    Prev
    Next
    INDEX
    Explanations

    verbs relating to responsibilities or duties

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to responsibility and obligations

    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
    thinkable
    -0.85
    skirts
    -0.73
    orks
    -0.70
    uncture
    -0.70
    amsung
    -0.69
    aucus
    -0.67
    cand
    -0.67
    tnc
    -0.65
    ensity
    -0.65
    rue
    -0.65
    POSITIVE LOGITS
     counterpart
    0.83
     foray
    0.81
     downfall
    0.77
     choice
    0.76
     asset
    0.75
     salvation
    0.74
     cousin
    0.71
     buddies
    0.71
     haul
    0.70
     defe
    0.70
    Activations Density 0.173%

    No Known Activations