© 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. 20470
    Prev
    Next
    INDEX
    Explanations

    negative or critical sentiments

    oai_token-act-pair · gpt-3.5-turbo

    negations and expressions of inability or disappointment

    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
     Allies
    -0.65
     reinstated
    -0.64
    assador
    -0.64
     applic
    -0.60
    liber
    -0.59
     significance
    -0.59
     embodiments
    -0.57
    pot
    -0.56
    ensible
    -0.55
     effectiveness
    -0.55
    POSITIVE LOGITS
     disappoint
    1.25
     hesitate
    1.13
     doubt
    1.04
     forget
    0.95
     forgetting
    0.93
     shy
    0.93
     envy
    0.89
     miss
    0.85
     fail
    0.84
     disappointed
    0.84
    Activations Density 0.276%

    No Known Activations