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

    Neuronpedia

    Jacobian LensNEW
    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. 2-RES-JB
    11. 19699
    Prev
    Next
    INDEX
    Explanations

    themes related to humanity and philosophical reflections on human nature

    oai_token-act-pair · gpt-3.5-turbo

    expressions of concern or sentiment regarding humanity

    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
    urations
    -0.84
    quart
    -0.71
    gur
    -0.70
     Gillespie
    -0.68
    acc
    -0.68
     |--
    -0.66
    olic
    -0.66
    kef
    -0.64
    UMP
    -0.63
    é¾įå
    -0.63
    POSITIVE LOGITS
     beings
    0.84
     humanity
    0.82
    icity
    0.79
     laureate
    0.76
     humankind
    0.75
     bom
    0.74
     civilisation
    0.73
     Pwr
    0.72
    ibia
    0.71
    ité
    0.71
    Activations Density 0.008%

    No Known Activations