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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18631
    Prev
    Next
    INDEX
    Explanations

    phrases referring to possible choices or actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions indicating methods or ways to accomplish something

    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
     Provided
    -0.85
     Klu
    -0.75
     Needs
    -0.72
     Conditions
    -0.70
     Appears
    -0.68
     Rhodes
    -0.68
     Boat
    -0.65
    Cho
    -0.65
     Notting
    -0.65
    ij士
    -0.64
    POSITIVE LOGITS
     communicate
    1.18
     accomplish
    1.16
     commemorate
    1.15
     achieve
    1.12
     differentiate
    1.10
     celebrate
    1.08
     organize
    1.08
     improve
    1.07
     visualize
    1.06
     motivate
    1.06
    Activations Density 0.061%

    No Known Activations