© 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. 4-RES-JB
    11. 19447
    Prev
    Next
    INDEX
    Explanations

    references to different types of licenses, particularly related to driving

    oai_token-act-pair · gpt-3.5-turbo

    references to licenses in various contexts, particularly driving licenses

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

    No Comments

    Negative Logits
     Lans
    -0.86
     Oo
    -0.79
    ilight
    -0.78
     Voy
    -0.69
    TING
    -0.68
    sonian
    -0.65
     IMAGES
    -0.65
     Unch
    -0.64
    anqu
    -0.64
    tl
    -0.63
    POSITIVE LOGITS
     licenses
    1.03
    license
    0.98
     license
    0.96
    License
    0.94
     holder
    0.88
     plate
    0.87
     licences
    0.86
     plates
    0.84
     licensing
    0.83
     licence
    0.83
    Activations Density 0.012%

    No Known Activations