© 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. 14064
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation and insight

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating perception or observation

    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
    ufact
    -0.75
    isure
    -0.73
     ensured
    -0.72
    assisted
    -0.70
    inqu
    -0.67
    keeping
    -0.65
    arist
    -0.64
    eta
    -0.63
     ensures
    -0.63
    fact
    -0.63
    POSITIVE LOGITS
     resemblance
    1.11
     similarities
    1.09
     difference
    1.04
     similarity
    0.97
     sunrise
    0.96
     parallels
    0.96
     signs
    0.95
     devastation
    0.95
     reflection
    0.91
     positives
    0.90
    Activations Density 0.175%

    No Known Activations