© 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. 13444
    Prev
    Next
    INDEX
    Explanations

    references to specific government entities or organizations with the word 'Authority' in their name

    oai_token-act-pair · gpt-3.5-turbo

    references to various authorities or organizations

    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
    lasses
    -0.98
    meyer
    -0.91
    ician
    -0.83
    matter
    -0.82
    ilde
    -0.80
    dn
    -0.78
    opher
    -0.77
    shaw
    -0.77
    mx
    -0.77
    eness
    -0.76
    POSITIVE LOGITS
    uthor
    0.84
     Authority
    0.83
     Employees
    0.78
    UTH
    0.76
    BILITIES
    0.76
    BILITY
    0.73
     Statistical
    0.73
     Executive
    0.71
     Board
    0.71
     Administrator
    0.71
    Activations Density 0.041%

    No Known Activations