© 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. 7-RES-JB
    11. 3822
    Prev
    Next
    INDEX
    Explanations

    terms related to various technical aspects like management, healthcare, software, government, intelligence, policy, and rights

    oai_token-act-pair · gpt-3.5-turbo

    nouns related to various fields or sectors, especially in the context of governance and health

    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
    aido
    -0.78
    irlf
    -0.77
    RAW
    -0.73
    lishes
    -0.71
    pora
    -0.70
    GMT
    -0.70
    anke
    -0.68
    emet
    -0.68
    Alias
    -0.68
    arya
    -0.67
    POSITIVE LOGITS
    tenance
    0.82
     hybrid
    0.73
     hybrids
    0.68
    osterone
    0.68
     establishments
    0.67
    ning
    0.66
     equival
    0.65
     extraord
    0.64
     complexes
    0.64
    roying
    0.64
    Activations Density 0.250%

    No Known Activations