© 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. 4-RES-JB
    11. 14893
    Prev
    Next
    INDEX
    Explanations

    astronomical terms related to constellations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to astronomy and constellations

    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
    oly
    -0.89
    bers
    -0.84
    iken
    -0.82
    lins
    -0.82
    employment
    -0.82
    kit
    -0.80
    assembly
    -0.79
    ber
    -0.79
    bern
    -0.78
    ufact
    -0.77
    POSITIVE LOGITS
     constellation
    1.12
     Gemini
    0.95
     Ascend
    0.93
     Asc
    0.84
     flares
    0.82
     Pluto
    0.81
     Polaris
    0.81
     Pis
    0.80
     Carbuncle
    0.76
     orbits
    0.73
    Activations Density 0.035%

    No Known Activations