Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 496
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or names of products

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly names associated with notable figures in sports and culture

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

    No Comments

    Negative Logits
    ivities
    -0.78
    ivity
    -0.76
    role
    -0.75
    Charges
    -0.74
    ources
    -0.72
    á½
    -0.69
    acity
    -0.68
    ators
    -0.67
    atography
    -0.66
    entity
    -0.66
    POSITIVE LOGITS
     Howe
    1.20
    shire
    0.90
    llers
    0.86
    ller
    0.83
    lla
    0.75
    bell
    0.72
    lly
    0.71
    vernment
    0.70
     Downs
    0.70
    monds
    0.69
    Activations Density 0.016%

    No Known Activations