© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 12355
    Prev
    Next
    INDEX
    Explanations

    filenames or paths

    oai_token-act-pair · gpt-3.5-turbo

    forward slashes, which may indicate image credits or separation of names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accordingly
    -0.82
     attent
    -0.73
     peanuts
    -0.72
     recons
    -0.71
     awaited
    -0.71
     tracks
    -0.70
     sooner
    -0.70
     dividends
    -0.69
     markings
    -0.69
     scaven
    -0.68
    POSITIVE LOGITS
    Getty
    1.32
    Flickr
    1.32
    Bloomberg
    1.22
    AFP
    1.22
    Courtesy
    1.13
    Reuters
    1.12
    Associated
    1.11
    CBC
    1.02
    Digital
    1.01
    Library
    0.98
    Activations Density 0.031%

    No Known Activations