© 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. 4-RES-JB
    11. 10265
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual and creative imagination

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating readiness and commitment

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

    No Comments

    Negative Logits
    Eastern
    -0.53
    Els
    -0.50
    erous
    -0.49
    los
    -0.49
     Adin
    -0.49
    Bridge
    -0.47
    ģ«
    -0.46
     Weir
    -0.46
     Alas
    -0.46
    hawks
    -0.46
    POSITIVE LOGITS
     yourself
    0.98
     yourselves
    0.86
     Yourself
    0.74
     YOUR
    0.73
     your
    0.72
    Your
    0.64
    your
    0.62
     Your
    0.60
    merce
    0.53
     NOTICE
    0.52
    Activations Density 1.054%

    No Known Activations