© 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. 20465
    Prev
    Next
    INDEX
    Explanations

    instances where things are described as contrasting or conflicting

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe contrast or comparison between different states or experiences

    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
    imar
    -0.70
    thora
    -0.64
    height
    -0.61
    Hispanic
    -0.60
    76561
    -0.60
    obia
    -0.60
     Bulgar
    -0.59
    BSD
    -0.59
    advant
    -0.58
    Ĭ±
    -0.58
    POSITIVE LOGITS
     actual
    1.24
     tangible
    0.99
    actual
    0.98
     real
    0.95
     offline
    0.91
     Actual
    0.90
     reality
    0.87
     courtroom
    0.85
     everyday
    0.83
     onstage
    0.81
    Activations Density 0.559%

    No Known Activations