© 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. 9-RES-JB
    11. 18383
    Prev
    Next
    INDEX
    Explanations

    phrases related to reasons or purposes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to legality and reasons associated with medical and political contexts

    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
    xon
    -0.71
    onet
    -0.66
    etheless
    -0.63
    former
    -0.61
    atars
    -0.61
    dB
    -0.60
    ilant
    -0.58
     beaten
    -0.57
    gall
    -0.57
    flat
    -0.57
    POSITIVE LOGITS
     purposes
    2.52
     reasons
    2.11
     sake
    2.07
     purpose
    1.79
     reason
    1.51
     Reasons
    1.35
    purpose
    1.18
     Purpose
    1.15
    ummies
    1.10
     convenience
    1.00
    Activations Density 0.580%

    No Known Activations