© 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. 11559
    Prev
    Next
    INDEX
    Explanations

    phrases related to time or change

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time or events occurring up to the present moment

    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
     Apostle
    -0.71
    accompan
    -0.65
    bed
    -0.64
     EntityItem
    -0.62
    Assembly
    -0.61
    Bon
    -0.60
    umbn
    -0.60
     Operation
    -0.59
    resa
    -0.59
     Carib
    -0.58
    POSITIVE LOGITS
    iatus
    0.80
    DEN
    0.79
    uyomi
    0.76
     unnoticed
    0.69
    ÄŁ
    0.67
    bery
    0.66
    í
    0.64
     ende
    0.63
    dk
    0.63
    hemy
    0.63
    Activations Density 0.040%

    No Known Activations