© 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. 2687
    Prev
    Next
    INDEX
    Explanations

    events related to outings and activities outside the home

    oai_token-act-pair · gpt-3.5-turbo

    activities related to leisure and family outings

    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
     singular
    -0.67
     reign
    -0.65
     remains
    -0.63
     Timeline
    -0.62
    stood
    -0.62
     legions
    -0.62
     rul
    -0.59
     unequivocally
    -0.58
     Appears
    -0.58
     stru
    -0.57
    POSITIVE LOGITS
     yesterday
    0.79
     when
    0.78
    ļéĨĴ
    0.76
    nesday
    0.72
     nearby
    0.71
     midday
    0.71
     shortly
    0.70
     preparing
    0.69
     asleep
    0.69
     earlier
    0.69
    Activations Density 0.408%

    No Known Activations