© 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. 6-RES-JB
    11. 2711
    Prev
    Next
    INDEX
    Explanations

    words related to "departments", particularly in the context of stores or organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to various departments, particularly in an organizational or institutional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Intent
    -0.68
    telling
    -0.67
    chers
    -0.63
     Pose
    -0.63
    Pause
    -0.62
    isers
    -0.62
    Mini
    -0.61
    fit
    -0.61
    pak
    -0.60
     Predators
    -0.59
    POSITIVE LOGITS
    al
    0.99
    alities
    0.97
    artments
    0.96
    artment
    0.95
    istry
    0.89
    ality
    0.87
    arians
    0.85
    alse
    0.83
    utical
    0.82
    ysis
    0.82
    Activations Density 0.022%

    No Known Activations