© 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. 5295
    Prev
    Next
    INDEX
    Explanations

    terms related to pressure or urgency

    oai_token-act-pair · gpt-3.5-turbo

    concepts and expressions related to pressure, opportunity, and significant discussions

    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
    poon
    -0.74
    Interstitial
    -0.62
    cot
    -0.62
    +.
    -0.58
    DERR
    -0.56
    dit
    -0.56
     ILCS
    -0.55
    zon
    -0.55
    ECA
    -0.55
     paran
    -0.55
    POSITIVE LOGITS
     persists
    1.04
     arises
    1.04
     seems
    1.02
     becomes
    1.02
     hasn
    1.01
     continues
    0.99
     goes
    0.99
     varies
    0.98
     isn
    0.98
     remains
    0.97
    Activations Density 0.357%

    No Known Activations