© 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. 2-RES-JB
    11. 15163
    Prev
    Next
    INDEX
    Explanations

    phrases related to lasting or continuous actions or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sustained" and its related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OTO
    -0.75
    onom
    -0.71
    arc
    -0.71
    aughty
    -0.66
    atography
    -0.66
    cross
    -0.65
    naire
    -0.65
    OTE
    -0.65
    naires
    -0.65
    osit
    -0.65
    POSITIVE LOGITS
     sustained
    0.98
     exha
    0.88
     veter
    0.88
     mathemat
    0.85
     destro
    0.85
     sustain
    0.83
     losses
    0.82
     tremend
    0.82
     unden
    0.77
     bouts
    0.76
    Activations Density 0.016%

    No Known Activations