© 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. 24058
    Prev
    Next
    INDEX
    Explanations

    the word "premier" with varying intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "premier" 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
    amus
    -0.83
    alle
    -0.82
    arettes
    -0.77
    azel
    -0.76
    apego
    -0.74
    gers
    -0.73
    dream
    -0.73
    uman
    -0.72
    psy
    -0.72
    urat
    -0.72
    POSITIVE LOGITS
     premier
    1.21
     premiere
    0.87
     certs
    0.86
     Premiere
    0.82
    è»
    0.78
    sonian
    0.78
     antioxid
    0.78
     "$:/
    0.77
    interstitial
    0.76
     premie
    0.75
    Activations Density 0.003%

    No Known Activations