© 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. 9-RES-JB
    11. 13199
    Prev
    Next
    INDEX
    Explanations

    phrases related to finalizing, completing, or resolving something

    oai_token-act-pair · gpt-3.5-turbo

    phrasal verbs indicating movement or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĥãĤ¯
    -0.74
     Defendants
    -0.67
    interstitial
    -0.61
     DRAG
    -0.60
    NEWS
    -0.60
    antry
    -0.58
    articles
    -0.58
    ourses
    -0.58
    vari
    -0.57
     Waves
    -0.56
    POSITIVE LOGITS
     cheaply
    0.87
     yourself
    0.82
     aloud
    0.80
     nicely
    0.78
    handedly
    0.76
     manually
    0.76
     loud
    0.76
     herself
    0.75
     yourselves
    0.75
     ourselves
    0.74
    Activations Density 0.176%

    No Known Activations