© 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. 7379
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that begin with "in order to."

    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
    listed
    -0.81
    heavy
    -0.66
     Gone
    -0.66
    option
    -0.65
    done
    -0.65
    checked
    -0.65
    calling
    -0.64
     Steps
    -0.63
     Rough
    -0.62
    written
    -0.62
    POSITIVE LOGITS
     achieve
    1.35
     satisfy
    1.31
     fulfill
    1.30
     maximize
    1.29
     preserve
    1.29
     create
    1.21
     compensate
    1.21
     facilitate
    1.20
     avoid
    1.19
     minimize
    1.19
    Activations Density 0.070%

    No Known Activations