© 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. 4460
    Prev
    Next
    INDEX
    Explanations

    references to the moon

    oai_token-act-pair · gpt-3.5-turbo

    references to the Moon

    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
    Interstitial
    -0.79
    iability
    -0.79
    ãĤ¢ãĥ«
    -0.74
    OUGH
    -0.74
    leneck
    -0.73
     IMAGES
    -0.72
    UCT
    -0.67
    irrel
    -0.67
    cha
    -0.67
    sburgh
    -0.66
    POSITIVE LOGITS
     Moon
    1.06
    beam
    1.02
    Moon
    0.90
    moon
    0.89
     Jae
    0.86
     moon
    0.82
    lit
    0.82
     rover
    0.78
     eclipse
    0.77
    walking
    0.76
    Activations Density 0.006%

    No Known Activations