© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 20173
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a particular company or brand

    oai_token-act-pair · gpt-3.5-turbo

    references to "Obsidian."

    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
    Fra
    -0.71
     Horowitz
    -0.69
    ////////////////////////////////
    -0.69
    boarding
    -0.67
    buster
    -0.67
     Das
    -0.65
    channelAvailability
    -0.63
    ted
    -0.62
    WAY
    -0.60
    Reviewer
    -0.60
    POSITIVE LOGITS
    idian
    1.43
    olesc
    1.39
    essional
    1.38
    olescent
    1.36
    essions
    1.27
    ensible
    1.25
    ervation
    1.16
    erving
    1.16
    erver
    1.13
    essed
    1.10
    Activations Density 0.038%

    No Known Activations