© 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 EvalsExportsinterp-engineNEWAPI 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. 23358
    Prev
    Next
    INDEX
    Explanations

    adjectives related to naturalness

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "natural" and its derivatives

    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
    andals
    -0.68
    ammy
    -0.67
    eters
    -0.64
    rero
    -0.64
    raped
    -0.61
    igmat
    -0.61
    rongh
    -0.61
    attery
    -0.60
    raph
    -0.59
     Miscellaneous
    -0.59
    POSITIVE LOGITS
     progression
    1.11
    istic
    0.93
     occurring
    0.92
     instinct
    0.91
     consequence
    0.87
     inclination
    0.86
    occ
    0.80
    istically
    0.79
     evolution
    0.78
     aspir
    0.78
    Activations Density 0.052%

    No Known Activations