© 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. 7-RES-JB
    11. 11034
    Prev
    Next
    INDEX
    Explanations

    words related to actions and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases indicating actions or processes

    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
    ces
    -0.74
    bidden
    -0.72
    ues
    -0.72
    isible
    -0.71
    thought
    -0.69
    gling
    -0.67
    flation
    -0.66
    UTC
    -0.66
    hooting
    -0.65
    doi
    -0.65
    POSITIVE LOGITS
     distribute
    1.27
     manipulate
    1.25
     collaborate
    1.23
     allocate
    1.23
     earn
    1.22
     engage
    1.20
     relocate
    1.20
     automate
    1.19
     promote
    1.19
     create
    1.18
    Activations Density 0.617%

    No Known Activations