© 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. 6-RES-JB
    11. 352
    Prev
    Next
    INDEX
    Explanations

    references to a specific entity or concept, possibly related to technology or business

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "data" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âķIJ
    -0.78
     tremend
    -0.75
     piercing
    -0.71
    shire
    -0.66
     destro
    -0.65
     widow
    -0.64
     parting
    -0.64
     Thumbnails
    -0.63
    ducers
    -0.63
     proportional
    -0.61
    POSITIVE LOGITS
    abases
    1.30
    etime
    1.01
    amation
    0.93
    alog
    0.88
    eman
    0.88
    emen
    0.86
    iverse
    0.85
    dat
    0.85
    Dat
    0.84
    agram
    0.84
    Activations Density 0.019%

    No Known Activations