© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 6567
    Prev
    Next
    INDEX
    Explanations

    URLs with a specific domain extension followed by a specific alphanumeric code

    oai_token-act-pair · gpt-3.5-turbo

    references to online resources and website links

    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
     Singer
    -0.81
    ATIVE
    -0.81
    OPER
    -0.78
     Excellence
    -0.76
     Exile
    -0.75
    Ãī
    -0.75
    ITION
    -0.74
     Gork
    -0.74
     Eighth
    -0.73
     Enabled
    -0.73
    POSITIVE LOGITS
    fc
    1.30
    iverpool
    1.29
    cf
    1.26
    cp
    1.25
    cs
    1.24
    bm
    1.23
    fs
    1.22
    bc
    1.21
    psc
    1.21
    vg
    1.20
    Activations Density 0.116%

    No Known Activations