© 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. 10001
    Prev
    Next
    INDEX
    Explanations

    words related to special activities, events, or designations

    oai_token-act-pair · gpt-3.5-turbo

    the repeated occurrence of the word "special"

    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
    •Special

    No Comments

    Negative Logits
    amus
    -0.76
    Į
    -0.67
    Ķ
    -0.67
    hari
    -0.65
    utsch
    -0.64
    ·
    -0.62
    shown
    -0.62
    absolute
    -0.62
    anon
    -0.60
    arer
    -0.59
    POSITIVE LOGITS
    ised
    1.30
    ties
    1.27
    izations
    1.21
    isations
    1.17
    ized
    1.01
    ities
    0.99
     relativity
    0.97
    ises
    0.96
    ity
    0.95
    ising
    0.95
    Activations Density 0.053%

    No Known Activations