© 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. 10-RES-JB
    11. 11299
    Prev
    Next
    INDEX
    Explanations

    phrases related to time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a range of starting and ending points or measures

    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
    iaz
    -0.84
    ubi
    -0.83
    iband
    -0.81
     Naz
    -0.81
    ML
    -0.80
    413
    -0.79
    412
    -0.78
     Riy
    -0.74
    bats
    -0.74
     Scrib
    -0.74
    POSITIVE LOGITS
     ends
    1.38
     ending
    1.36
     END
    1.27
     Ending
    1.27
     endings
    1.26
     Ends
    1.23
     termin
    1.15
     end
    1.13
     finale
    1.11
    EGIN
    1.10
    Activations Density 0.159%

    No Known Activations