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. 20995
    Prev
    Next
    INDEX
    Explanations

    words related to authority or imposition

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "by" used in various contexts

    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
    apest
    -0.93
    atever
    -0.79
    iltration
    -0.77
    ATIONAL
    -0.75
    oother
    -0.74
    ADRA
    -0.73
    aser
    -0.71
    amera
    -0.70
    atche
    -0.70
    raq
    -0.69
    POSITIVE LOGITS
     virtue
    1.01
    laws
    0.84
    products
    0.75
     Seeking
    0.69
     Dame
    0.68
    gone
    0.66
     Aure
    0.66
     Tre
    0.65
     statute
    0.65
     Unt
    0.65
    Activations Density 0.144%

    No Known Activations