© 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. 9972
    Prev
    Next
    INDEX
    Explanations

    phrases suggesting different options or choices that individuals or groups can make

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest conditional actions or choices

    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
     Leban
    -0.73
     totality
    -0.69
     Sacrament
    -0.58
     Daisy
    -0.58
    Reply
    -0.58
     firsthand
    -0.58
     distinguishing
    -0.58
     emanating
    -0.57
     Everyday
    -0.57
    interstitial
    -0.56
    POSITIVE LOGITS
    'll
    1.57
    'd
    1.28
     could
    1.01
    're
    1.01
     might
    1.00
    might
    0.98
    could
    0.98
     dunno
    0.95
    've
    0.89
    eding
    0.87
    Activations Density 0.172%

    No Known Activations