© 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. 9-RES-JB
    11. 13141
    Prev
    Next
    INDEX
    Explanations

    descriptions of the process or requirements for a specific task or project, possibly related to web development

    oai_token-act-pair · gpt-3.5-turbo

    references to web development projects or related undertakings

    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
    Not in Any Lists

    No Comments

    Negative Logits
    anooga
    -0.71
    ļéĨĴ
    -0.67
    sequently
    -0.66
    ultane
    -0.65
    displayText
    -0.62
    umerous
    -0.61
     srf
    -0.61
    anwhile
    -0.61
    plete
    -0.60
    ô
    -0.60
    POSITIVE LOGITS
     atheists
    0.77
     nostalgia
    0.75
     cynicism
    0.73
     Orwell
    0.73
     Canaver
    0.72
     hypocrisy
    0.72
     utopian
    0.72
     sentimental
    0.71
     philosophers
    0.68
     stupidity
    0.68
    Activations Density 1.049%

    No Known Activations