Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 7102
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the passage of time or activities over time

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to personal experiences

    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
    circle
    -0.67
    agate
    -0.61
    adi
    -0.60
    ONSORED
    -0.60
     DEFENSE
    -0.59
     Defeat
    -0.58
    rices
    -0.58
     slate
    -0.55
     carriers
    -0.55
    Compat
    -0.53
    POSITIVE LOGITS
     winters
    0.94
     summers
    0.93
     nights
    0.86
     eternity
    0.82
     slee
    0.81
     weekends
    0.80
     time
    0.77
    anmar
    0.77
     waking
    0.75
     Sundays
    0.74
    Activations Density 0.123%

    No Known Activations