© 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. 3-RES-JB
    11. 16304
    Prev
    Next
    INDEX
    Explanations

    phrases related to breaking something

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the act of breaking down or reducing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kenya
    -0.68
    âģ
    -0.64
     Clo
    -0.59
    mong
    -0.58
    #$
    -0.57
    ://
    -0.57
     Huck
    -0.56
     acqu
    -0.56
    ught
    -0.55
     �
    -0.55
    POSITIVE LOGITS
    stairs
    1.10
    grading
    1.05
    river
    1.05
    graded
    0.96
    grades
    0.88
    LOAD
    0.79
    lease
    0.77
    pour
    0.76
    stem
    0.76
    haul
    0.76
    Activations Density 0.045%

    No Known Activations