© 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. 11-RES-JB
    11. 1363
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer hardware and networking

    oai_token-act-pair · gpt-3.5-turbo

    specific model identifiers and version numbers in the context of technology and hardware

    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
    idays
    -0.75
    things
    -0.72
     clos
    -0.67
    inations
    -0.67
     wiser
    -0.67
    cients
    -0.65
     snowball
    -0.65
    selves
    -0.65
    eners
    -0.65
     passions
    -0.65
    POSITIVE LOGITS
    KT
    1.28
    GD
    1.24
    BW
    1.20
    MQ
    1.19
    CV
    1.15
    BT
    1.15
    DH
    1.15
    UA
    1.14
    JM
    1.14
    BG
    1.14
    Activations Density 0.124%

    No Known Activations