© 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. 8-RES-JB
    11. 6440
    Prev
    Next
    INDEX
    Explanations

    phrases related to meeting or not meeting expectations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to meeting or failing to meet expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lees
    -0.76
    controlled
    -0.76
    verning
    -0.69
    affected
    -0.69
    wallet
    -0.68
    gan
    -0.67
    ciation
    -0.67
    ucl
    -0.66
    usc
    -0.65
    SELECT
    -0.65
    POSITIVE LOGITS
     expectations
    1.06
     hype
    0.92
     stereotypes
    0.85
     standards
    0.79
     Tradition
    0.78
     tradition
    0.75
     scrutiny
    0.73
     stereotype
    0.73
     expectation
    0.71
     Prometheus
    0.70
    Activations Density 0.077%

    No Known Activations