© 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. 2-RES-JB
    11. 18220
    Prev
    Next
    INDEX
    Explanations

    references to celestial bodies, particularly stars

    oai_token-act-pair · gpt-3.5-turbo

    the term "star" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.94
    apons
    -0.92
    veyard
    -0.91
    nsic
    -0.87
    »Ĵ
    -0.86
    odcast
    -0.84
    Ń·
    -0.82
    etimes
    -0.81
    Downloadha
    -0.79
    ĵĺ
    -0.78
    POSITIVE LOGITS
     star
    0.97
     stars
    0.94
    star
    0.90
    stars
    0.84
    light
    0.83
    liner
    0.82
    burst
    0.82
    bucks
    0.81
    fish
    0.76
    stri
    0.76
    Activations Density 0.017%

    No Known Activations