© 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 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. 13857
    Prev
    Next
    INDEX
    Explanations

    names or entities related to professional titles

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms in text

    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
    ichick
    -0.73
    cca
    -0.69
    taboola
    -0.67
    glers
    -0.65
    gie
    -0.64
    gg
    -0.63
     Huff
    -0.63
    vae
    -0.63
    alam
    -0.61
    ger
    -0.60
    POSITIVE LOGITS
    ITION
    1.24
    MENT
    1.10
    IFIED
    1.10
    REC
    1.07
    LEY
    1.07
    ICLE
    1.06
    OLOGY
    1.04
    IL
    1.02
    NER
    1.02
    EMENT
    1.02
    Activations Density 0.116%

    No Known Activations