© 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. 0-RES-JB
    11. 6354
    Prev
    Next
    INDEX
    Explanations

    features or key components in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of features or specifications of products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overtime
    -0.70
     slowed
    -0.68
     collective
    -0.68
     renewed
    -0.67
     rocket
    -0.67
     sovereign
    -0.67
     club
    -0.67
     delinquent
    -0.66
     accelerated
    -0.65
     rallying
    -0.65
    POSITIVE LOGITS
     Features
    3.71
    Features
    2.36
     Feature
    1.88
    Feature
    1.69
    features
    1.62
    ATURES
    1.39
     Includes
    1.30
     Specifications
    1.28
     Ingredients
    1.27
     Included
    1.25
    Activations Density 0.040%

    No Known Activations