© 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. 7-RES-JB
    11. 8484
    Prev
    Next
    INDEX
    Explanations

    words related to staff and personnel matters

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "staff" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fem
    -0.80
     arous
    -0.73
    ICO
    -0.67
    pend
    -0.65
     Roosevelt
    -0.64
    eering
    -0.63
     Sham
    -0.62
    ibia
    -0.62
     Pac
    -0.62
     fem
    -0.62
    POSITIVE LOGITS
    member
    1.06
     members
    1.03
    members
    1.01
     member
    0.98
     sergeant
    0.92
    atcher
    0.87
    emouth
    0.83
    irtual
    0.82
    iencies
    0.79
     Members
    0.75
    Activations Density 0.036%

    No Known Activations