© 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. 24210
    Prev
    Next
    INDEX
    Explanations

    proper nouns or titles of authority figures

    oai_token-act-pair · gpt-3.5-turbo

    references to leadership or individuals in control

    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
     chloride
    -0.62
     Territories
    -0.60
     isol
    -0.59
     Channel
    -0.59
    Avg
    -0.57
     Mex
    -0.56
    avez
    -0.56
     Meridian
    -0.56
    aneously
    -0.56
    Prot
    -0.56
    POSITIVE LOGITS
    pin
    1.01
    butt
    0.94
    pins
    0.93
    pring
    0.90
    quarters
    0.88
    lasses
    0.87
    canon
    0.87
    paces
    0.84
    quarter
    0.84
    phones
    0.82
    Activations Density 0.012%

    No Known Activations