© 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. 21549
    Prev
    Next
    INDEX
    Explanations

    strong emotions or impactful situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate strength or significance in various contexts

    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
    anners
    -0.90
    breakers
    -0.83
     creations
    -0.81
    friends
    -0.81
     Actions
    -0.81
    aunts
    -0.80
     endeavors
    -0.80
     ventures
    -0.80
    Ts
    -0.79
    devices
    -0.79
    POSITIVE LOGITS
     possibility
    1.38
     tendency
    1.28
     difference
    1.27
     overlap
    1.23
     discrepancy
    1.22
     chance
    1.21
     correlation
    1.19
     similarity
    1.18
     misconception
    1.17
     shortage
    1.17
    Activations Density 0.175%

    No Known Activations