© 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. 6-RES-JB
    11. 18931
    Prev
    Next
    INDEX
    Explanations

    phrases related to time, specifically referring to the past or future

    oai_token-act-pair · gpt-3.5-turbo

    references to time, specifically past and future events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifle
    -0.80
    ikh
    -0.79
    hyde
    -0.76
    iphate
    -0.74
    ucker
    -0.73
    addle
    -0.71
    apist
    -0.71
    iece
    -0.70
    igate
    -0.70
    ère
    -0.69
    POSITIVE LOGITS
     generations
    1.22
     developments
    1.01
     iterations
    0.99
     circumstances
    0.90
     trends
    0.90
     orders
    0.90
     events
    0.89
     versions
    0.89
     occurrences
    0.89
     realities
    0.88
    Activations Density 0.155%

    No Known Activations