© 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. 10-RES-JB
    11. 11515
    Prev
    Next
    INDEX
    Explanations

    numerical ratings in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    numeric values related to ratings or scores

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.67
    á½
    -0.56
    tein
    -0.54
     HUM
    -0.53
    nces
    -0.53
     Angle
    -0.53
    âĢİ
    -0.52
     suffice
    -0.51
     Explos
    -0.51
    chin
    -0.51
    POSITIVE LOGITS
    awaru
    0.67
    ubi
    0.67
    soDeliveryDate
    0.64
    Repeat
    0.64
    CLUD
    0.63
    arthed
    0.62
    independence
    0.62
    rounded
    0.59
     payday
    0.59
     CoC
    0.59
    Activations Density 0.021%

    No Known Activations