© 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. 9-RES-JB
    11. 4167
    Prev
    Next
    INDEX
    Explanations

    phrases related to giving suggestions or instructions

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ´ãĥ³
    -0.86
     Beginning
    -0.64
    VERTISEMENT
    -0.64
    ONSORED
    -0.61
     JPM
    -0.60
    BuyableInstoreAndOnline
    -0.59
     Bagg
    -0.59
     Argon
    -0.58
    byss
    -0.58
     powered
    -0.57
    POSITIVE LOGITS
     you
    0.84
     yeah
    0.83
     don
    0.82
     behave
    0.81
     shouldn
    0.81
    don
    0.79
     assassinate
    0.79
    want
    0.79
     please
    0.78
    cius
    0.77
    Activations Density 0.347%

    No Known Activations