© 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. 10-RES-JB
    11. 20297
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a critical opinion or judgement

    oai_token-act-pair · gpt-3.5-turbo

    phrases that convey the concept of understanding or clarity

    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
     Lens
    -0.66
    amiya
    -0.63
    CRE
    -0.63
    Aff
    -0.61
     stewards
    -0.59
    meet
    -0.57
    sha
    -0.57
    rifice
    -0.55
     retri
    -0.55
     Presence
    -0.55
    POSITIVE LOGITS
     drift
    0.87
     gist
    0.81
     twisted
    0.73
     vibe
    0.72
    chy
    0.70
    ©¶æ
    0.66
    oglu
    0.66
     impression
    0.66
    patrick
    0.64
     feeling
    0.63
    Activations Density 0.148%

    No Known Activations