© 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. 0-RES-JB
    11. 9770
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to a negative or extreme context

    oai_token-act-pair · gpt-3.5-turbo

    negative descriptors related to situations or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     woo
    -0.65
     further
    -0.63
     self
    -0.61
     Montana
    -0.60
     capital
    -0.60
     CC
    -0.60
     co
    -0.59
     mapping
    -0.58
     virtual
    -0.58
     profess
    -0.58
    POSITIVE LOGITS
    rible
    3.99
    ribly
    2.29
    rors
    1.23
    ulhu
    1.20
    rity
    1.11
    rified
    1.11
    ricane
    1.08
    yrinth
    1.08
    rats
    1.04
    riter
    1.03
    Activations Density 0.021%

    No Known Activations