© 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. 20465
    Prev
    Next
    INDEX
    Explanations

    phrases describing the physical attributes or characteristics of objects or environments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "K"

    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
     laureate
    -0.67
     diapers
    -0.64
    terday
    -0.64
     wip
    -0.63
     expires
    -0.63
    Ø©
    -0.61
     commons
    -0.60
     Collider
    -0.60
     Thumbnails
    -0.60
     heads
    -0.60
    POSITIVE LOGITS
    orea
    1.18
    eeper
    1.12
    atherine
    1.10
    EEP
    1.08
    laus
    1.08
    ratom
    1.07
    ernel
    1.06
    rieg
    1.06
    essel
    1.06
    icking
    1.06
    Activations Density 0.040%

    No Known Activations