© 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. 10-RES-JB
    11. 4365
    Prev
    Next
    INDEX
    Explanations

    phrases indicating significance or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the significance or impact of certain elements or features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    renheit
    -0.83
    ipel
    -0.66
    jong
    -0.66
    FIL
    -0.66
    cape
    -0.66
    ilaterally
    -0.65
    ORTS
    -0.65
    nery
    -0.65
    ruary
    -0.64
    ilded
    -0.64
    POSITIVE LOGITS
     thing
    1.51
     downside
    1.47
     drawback
    1.42
     caveat
    1.42
     takeaway
    1.41
     question
    1.33
     difference
    1.30
     implication
    1.27
     aspect
    1.25
     problem
    1.25
    Activations Density 0.149%

    No Known Activations