© 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. 9-RES-JB
    11. 9956
    Prev
    Next
    INDEX
    Explanations

    specific numbers related to income levels

    oai_token-act-pair · gpt-3.5-turbo

    sections that describe large creatures or characters

    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
    warts
    -0.72
    anced
    -0.68
    abol
    -0.67
    agan
    -0.66
    verend
    -0.64
     symmetry
    -0.64
    venge
    -0.64
    bread
    -0.63
    ufact
    -0.63
    ancing
    -0.61
    POSITIVE LOGITS
    px
    0.98
     MHz
    0.97
    KING
    0.93
    MHz
    0.92
    +
    0.91
    000
    0.87
    mAh
    0.87
    +.
    0.86
    Hz
    0.86
    +,
    0.84
    Activations Density 0.091%

    No Known Activations