© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 18445
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Marvel movie "Guardians of the Galaxy"

    oai_token-act-pair · gpt-3.5-turbo

    references to the "Guardians of the Galaxy."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prone
    -0.68
     bilingual
    -0.66
     susceptibility
    -0.66
    uliffe
    -0.66
     reper
    -0.65
     tracing
    -0.64
     disag
    -0.64
    fman
    -0.63
     secretaries
    -0.63
     penetrating
    -0.63
    POSITIVE LOGITS
     Universe
    0.85
     Sabha
    0.81
     Centauri
    0.79
     Detail
    0.76
     Galaxy
    0.74
    ¥µ
    0.72
    lake
    0.71
    estern
    0.71
     Skydragon
    0.70
    venth
    0.69
    Activations Density 0.097%

    No Known Activations