© 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. 6-RES-JB
    11. 2871
    Prev
    Next
    INDEX
    Explanations

    phrases related to the city or place named "Med"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Med" or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chnology
    -0.81
    ngth
    -0.67
     innocence
    -0.67
     Wilde
    -0.63
    AUT
    -0.63
    ãģį
    -0.62
    holding
    -0.62
    ãĤ©
    -0.61
     Orwell
    -0.61
    =-=-=-=-=-=-=-=-
    -0.60
    POSITIVE LOGITS
    iterranean
    1.11
    itations
    1.10
    ications
    1.09
    allion
    1.08
    ication
    1.04
    ient
    1.03
    iator
    1.03
    itated
    1.02
    itating
    0.99
    ieval
    0.98
    Activations Density 0.019%

    No Known Activations