© 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. 8636
    Prev
    Next
    INDEX
    Explanations

    phrases related to regulations and penalties involving monetary fines

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating limits or maximum quantities

    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
     Fidel
    -0.67
     sting
    -0.59
    Maker
    -0.59
     Munich
    -0.58
    ¯¯¯¯
    -0.58
     Persian
    -0.58
    [/
    -0.57
     Emanuel
    -0.56
     Abyss
    -0.56
     Fit
    -0.56
    POSITIVE LOGITS
    grades
    1.01
    graded
    0.98
    votes
    0.92
    grading
    0.88
    rights
    0.85
    raised
    0.85
    np
    0.83
    osponsors
    0.78
    icum
    0.78
    regulation
    0.77
    Activations Density 0.041%

    No Known Activations