© 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. 11-RES-JB
    11. 18670
    Prev
    Next
    INDEX
    Explanations

    technical specifications and details about products

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and features of products

    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
    speech
    -0.84
    knowledge
    -0.82
    conscious
    -0.82
    watching
    -0.80
    Screenshot
    -0.80
    Flickr
    -0.79
    job
    -0.78
    podcast
    -0.77
    someone
    -0.77
    aminer
    -0.76
    POSITIVE LOGITS
     versions
    1.59
     models
    1.54
     variants
    1.54
     varieties
    1.43
     editions
    1.41
     configurations
    1.27
     kits
    1.26
     sizes
    1.25
     batches
    1.25
     units
    1.22
    Activations Density 0.472%

    No Known Activations