© 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. 4434
    Prev
    Next
    INDEX
    Explanations

    acronyms commonly associated with television networks

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

    references to "CS" or related designations, likely indicating a focus on media channels or entities associated with that term

    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
    sup
    -0.56
     amput
    -0.56
     Scotch
    -0.54
    sc
    -0.53
    tis
    -0.52
    itsch
    -0.52
     longer
    -0.51
     nearer
    -0.51
    accompanied
    -0.50
    Äĩ
    -0.50
    POSITIVE LOGITS
    IRO
    1.28
    GO
    0.97
    RF
    0.95
    KA
    0.90
    UF
    0.89
    UL
    0.78
    QUIRE
    0.75
    NL
    0.74
    CEPT
    0.73
    RM
    0.73
    Activations Density 0.033%

    No Known Activations