© 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. 7-RES-JB
    11. 10024
    Prev
    Next
    INDEX
    Explanations

    words related to the astronomical concept of Pluto

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "plu" in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /-
    -0.64
     dearly
    -0.64
     Ancients
    -0.60
     renown
    -0.58
     Advocate
    -0.58
     Emirates
    -0.57
     Reincarn
    -0.57
     Nightmares
    -0.55
     Advertisement
    -0.54
    recomm
    -0.54
    POSITIVE LOGITS
    atory
    0.79
    ocene
    0.73
    istics
    0.72
    м
    0.72
    ified
    0.71
    abil
    0.70
    eworks
    0.69
    hetto
    0.69
    ifies
    0.68
    hett
    0.68
    Activations Density 0.111%

    No Known Activations