© 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. 11-RES-JB
    11. 21923
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters and seemingly random text, potentially in a list format

    oai_token-act-pair · gpt-3.5-turbo

    metrics and evaluations related to products or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adversary
    -0.67
     presumptive
    -0.64
     stringent
    -0.60
     laying
    -0.60
     segreg
    -0.59
     nonexistent
    -0.59
     mismatch
    -0.58
    )",
    -0.58
     establish
    -0.58
    acter
    -0.57
    POSITIVE LOGITS
    <|endoftext|>
    1.42
    Advertisements
    1.31
     Comments
    1.24
    Comments
    1.16
     Tags
    1.10
     Donation
    1.06
     âĿ
    1.03
    Featured
    1.03
     Written
    1.01
     ·
    0.99
    Activations Density 0.540%

    No Known Activations