© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finally" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "finally," indicating a sense of resolution or completion

    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
    lav
    -0.75
     Akin
    -0.74
    pill
    -0.68
    maid
    -0.67
    ĺħ
    -0.66
    cycle
    -0.63
    regate
    -0.62
    river
    -0.61
    men
    -0.61
     Bohem
    -0.61
    POSITIVE LOGITS
     reunited
    1.03
     relent
    1.01
     succumbed
    0.90
    icably
    0.85
     reconcil
    0.84
     succumb
    0.84
    éĹĺ
    0.83
     succeeded
    0.82
     reun
    0.81
     nailed
    0.78
    Activations Density 0.047%

    No Known Activations