© 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. 11-RES-JB
    11. 7004
    Prev
    Next
    INDEX
    Explanations

    phrases related to job positions or roles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating potential actions or considerations regarding candidates and appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.84
    abiding
    -0.78
    Statistics
    -0.78
    ãĤ¦ãĤ¹
    -0.77
    breeding
    -0.75
     Printed
    -0.72
    artifacts
    -0.71
     ILCS
    -0.70
    maps
    -0.68
    IQ
    -0.67
    POSITIVE LOGITS
     resign
    1.55
     endorse
    1.30
     succeed
    1.30
     appoint
    1.30
     nominate
    1.29
     retire
    1.24
     govern
    1.23
     become
    1.19
     oversee
    1.19
     inherit
    1.16
    Activations Density 0.252%

    No Known Activations