© 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. 9-RES-JB
    11. 18485
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completion or accomplishment

    oai_token-act-pair · gpt-3.5-turbo

    instances of achievement or success after a period of effort or waiting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     constantly
    -0.73
     hither
    -0.68
     unsu
    -0.63
    ously
    -0.62
     portfolios
    -0.61
     inaccur
    -0.60
     inferred
    -0.59
    Lear
    -0.59
     fictitious
    -0.59
     continually
    -0.59
    POSITIVE LOGITS
     relent
    0.92
     reckoning
    0.89
     sanity
    0.87
    enough
    0.85
    Enough
    0.84
     acknowledgement
    0.81
     grasp
    0.78
     fruition
    0.78
     realization
    0.78
     closure
    0.75
    Activations Density 0.311%

    No Known Activations