© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 3052
    Prev
    Next
    INDEX
    Explanations

    phrases describing conditions or requirements for actions to be effective

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to necessity and effectiveness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arat
    -0.74
     disappro
    -0.68
     Annotations
    -0.66
    )</
    -0.63
    rans
    -0.61
     </
    -0.61
    uploads
    -0.60
    iliar
    -0.60
    ogly
    -0.60
    {{
    -0.58
    POSITIVE LOGITS
    must
    0.72
     multiply
    0.71
     must
    0.66
     requires
    0.64
     Maxwell
    0.64
    dfx
    0.63
    ign
    0.63
     GOODMAN
    0.63
    igne
    0.62
    apo
    0.61
    Activations Density 0.204%

    No Known Activations