© 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. 7091
    Prev
    Next
    INDEX
    Explanations

    references to objects and locations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "in" within sentences

    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
     incumb
    -0.72
    idays
    -0.65
    llor
    -0.61
    NOW
    -0.59
    illian
    -0.59
    izophren
    -0.57
    emo
    -0.57
     embold
    -0.57
     informed
    -0.56
    phans
    -0.56
    POSITIVE LOGITS
     lieu
    1.32
    animate
    1.22
    clusions
    1.18
     accordance
    1.11
    ked
    1.11
     conjunction
    1.10
    between
    1.08
     situ
    1.08
    escap
    1.04
     front
    1.02
    Activations Density 0.288%

    No Known Activations