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

    Neuronpedia

    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. 7-RES-JB
    11. 1981
    Prev
    Next
    INDEX
    Explanations

    names or words related to various entities or topics, such as Enron

    oai_token-act-pair · gpt-3.5-turbo

    mentions of an entity abbreviated as "En."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UGH
    -0.71
     Heights
    -0.69
    ij士
    -0.67
     hitch
    -0.65
    TPPStreamerBot
    -0.64
    sburgh
    -0.63
     flats
    -0.62
     independently
    -0.61
     distortion
    -0.61
    DragonMagazine
    -0.60
    POSITIVE LOGITS
    viron
    1.31
    closure
    1.12
    chanted
    1.12
    forcer
    1.09
    rollment
    1.09
    zyme
    1.08
    closed
    1.05
    riched
    1.04
    semble
    1.04
    cyclop
    1.03
    Activations Density 0.019%

    No Known Activations