© 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. 10-RES-JB
    11. 12308
    Prev
    Next
    INDEX
    Explanations

    specific and detailed technical terms or phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to various data entities and their relationships

    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
    enance
    -0.73
    BIL
    -0.70
    ophobia
    -0.69
     scorn
    -0.69
    ledge
    -0.69
    hetamine
    -0.67
    anus
    -0.67
    ognitive
    -0.67
    ynchronous
    -0.67
    avior
    -0.65
    POSITIVE LOGITS
     chapters
    1.37
     batches
    1.36
     sites
    1.35
     editions
    1.29
     folders
    1.29
     stations
    1.26
     regions
    1.25
     departments
    1.23
     projects
    1.23
     sessions
    1.21
    Activations Density 0.434%

    No Known Activations