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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 1923
    Prev
    Next
    INDEX
    Explanations

    JavaScript-related functions or programming methods that include the word "return" and may return a specific value

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to programming functions and operations

    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
    forum
    -0.85
     Hutch
    -0.84
    forums
    -0.82
    odcast
    -0.81
    otics
    -0.79
    fires
    -0.77
    thren
    -0.76
    iere
    -0.75
    utch
    -0.74
    ashi
    -0.73
    POSITIVE LOGITS
     integers
    1.41
     integer
    1.37
     bytes
    1.34
     UTF
    1.30
     byte
    1.22
     JSON
    1.21
     Integer
    1.19
     Unicode
    1.15
     formatted
    1.15
     ASCII
    1.15
    Activations Density 0.330%

    No Known Activations