© 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. 6-RES-JB
    11. 13843
    Prev
    Next
    INDEX
    Explanations

    specific phrases related to different events, such as press releases, meetings, and interviews, with an emphasis on individuals' names

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of sentence endings or periods in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     affili
    -0.80
     helper
    -0.78
     ally
    -0.76
     oxide
    -0.68
     silent
    -0.68
     muscle
    -0.68
     disbel
    -0.68
     workforce
    -0.68
     arm
    -0.68
     agent
    -0.68
    POSITIVE LOGITS
     Previously
    1.17
     Nevertheless
    1.13
     Presumably
    1.12
     Recall
    1.11
     Whereas
    1.11
     Specifically
    1.11
     Fortunately
    1.10
     Therefore
    1.09
     Essentially
    1.09
     Granted
    1.08
    Activations Density 0.904%

    No Known Activations