© 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. 12-RES-JB
    11. 4114
    Prev
    Next
    INDEX
    Explanations

    details about a person's career progression and accomplishments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to editorial roles and positions in journalism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    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
     EEG
    -0.76
     horm
    -0.69
     therap
    -0.69
    chwitz
    -0.68
     danced
    -0.68
     indo
    -0.67
    \\\\
    -0.66
     pregn
    -0.64
    ober
    -0.64
    aband
    -0.63
    POSITIVE LOGITS
     journalism
    1.71
     newspaper
    1.71
     editorial
    1.70
     Newspaper
    1.70
     newspapers
    1.70
     editors
    1.65
     Newsp
    1.62
     Journalism
    1.59
     Pulitzer
    1.57
     editor
    1.53
    Activations Density 0.661%

    No Known Activations