© 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. 10-RES-JB
    11. 12773
    Prev
    Next
    INDEX
    Explanations

    commands and instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of commands or instructions related to system processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.93
    ylum
    -0.77
    /#
    -0.71
    Untitled
    -0.70
    philis
    -0.69
    ãĥİ
    -0.69
    ldom
    -0.68
     grievances
    -0.68
     openly
    -0.68
     resigned
    -0.66
    POSITIVE LOGITS
     designers
    1.26
     engineers
    1.23
     researchers
    1.21
     developers
    1.18
     investigators
    1.17
     planners
    1.16
     reviewers
    1.16
     programmers
    1.15
     clinicians
    1.15
     marketers
    1.15
    Activations Density 0.450%

    No Known Activations