© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal issues

    oai_token-act-pair · gpt-3.5-turbo

    sentences that convey a strong opinion or conclusion

    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
     honored
    -0.88
     honoring
    -0.84
     coloring
    -0.83
     flavorful
    -0.81
    agin
    -0.78
     bullpen
    -0.76
     restroom
    -0.76
    plet
    -0.75
     enrollment
    -0.75
     flavored
    -0.74
    POSITIVE LOGITS
     Whilst
    1.62
     Firstly
    1.31
     Alternatively
    1.29
     Labour
    1.21
     Hence
    1.17
     Afterwards
    1.16
     Nato
    1.16
     Consequently
    1.15
     Ukip
    1.14
     Similarly
    1.11
    Activations Density 0.848%

    No Known Activations