© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 7007
    Prev
    Next
    INDEX
    Explanations

    durations of time expressed in numbers and words

    oai_token-act-pair · gpt-3.5-turbo

    numeric values indicating quantity or duration

    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
     Caption
    -0.64
     moderator
    -0.59
     distinction
    -0.58
     turnout
    -0.57
    rike
    -0.56
     likeness
    -0.56
     abbre
    -0.56
    artisan
    -0.55
    Pad
    -0.54
    Else
    -0.53
    POSITIVE LOGITS
     consecutive
    1.20
     years
    1.20
     weeks
    1.19
     months
    1.18
     hours
    1.12
     days
    1.12
     minutes
    1.08
    months
    1.08
     seasons
    1.05
     generations
    1.02
    Activations Density 0.190%

    No Known Activations