© 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. 1-RES-JB
    11. 16895
    Prev
    Next
    INDEX
    Explanations

    phrases related to directions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    keywords and phrases related to focus and attention in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enei
    -0.58
    javascript
    -0.56
    76561
    -0.54
    cffffcc
    -0.53
    fecture
    -0.50
    bryce
    -0.49
    adow
    -0.48
    Offline
    -0.48
    natureconservancy
    -0.47
    \":
    -0.47
    POSITIVE LOGITS
    ONSORED
    0.71
    ogether
    0.59
     Costs
    0.57
    VERTISEMENT
    0.55
    ividual
    0.51
     Requirements
    0.50
    ometime
    0.50
     Events
    0.48
     Beans
    0.48
    respective
    0.48
    Activations Density 3.801%

    No Known Activations