© 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. 11-RES-JB
    11. 2760
    Prev
    Next
    INDEX
    Explanations

    phrases related to critiques or evaluations of something

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and drama in dialogue or narrative style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imity
    -0.73
    Newsletter
    -0.70
     Occupations
    -0.68
    encers
    -0.68
    rica
    -0.66
    æ©
    -0.66
    atri
    -0.65
    âĸł
    -0.65
    acteria
    -0.65
    versions
    -0.65
    POSITIVE LOGITS
     hey
    1.27
     fuck
    1.23
     yeah
    1.22
     dunno
    1.19
     oh
    1.19
     godd
    1.19
     okay
    1.18
     alright
    1.18
     goddamn
    1.17
    yeah
    1.17
    Activations Density 0.566%

    No Known Activations