© 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. 8-RES-JB
    11. 22432
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of being open or receptive to new ideas or information

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "open" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tycoon
    -0.76
     Lumpur
    -0.74
     Brach
    -0.73
     Lowry
    -0.68
     Phi
    -0.68
     UD
    -0.68
     Mara
    -0.68
     Mons
    -0.67
     Mermaid
    -0.65
     Khan
    -0.65
    POSITIVE LOGITS
    minded
    1.12
    eyed
    1.09
    ended
    1.07
    source
    1.01
    skinned
    0.99
    spoken
    0.93
    facing
    0.92
    thinking
    0.92
    door
    0.92
    advertising
    0.91
    Activations Density 0.033%

    No Known Activations