© 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. 7263
    Prev
    Next
    INDEX
    Explanations

    words related to assertion and conflict

    oai_token-act-pair · gpt-3.5-turbo

    expressions of anger or frustration

    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
    rax
    -0.57
     Wikimedia
    -0.53
    raz
    -0.53
    aro
    -0.52
     scanners
    -0.52
    anyl
    -0.51
    NW
    -0.51
    ella
    -0.51
    Wi
    -0.50
    pak
    -0.49
    POSITIVE LOGITS
    tenance
    0.72
    ibilities
    0.72
    EMENT
    0.65
    uated
    0.64
    ª
    0.62
    ATIONAL
    0.61
    ificant
    0.60
    ABLE
    0.59
    erate
    0.59
    ories
    0.59
    Activations Density 0.352%

    No Known Activations