© 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. 4298
    Prev
    Next
    INDEX
    Explanations

    terms related to negotiations or discussions

    oai_token-act-pair · gpt-3.5-turbo

    references to obstacles or challenges in various contexts

    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
     whilst
    -0.83
     fucking
    -0.72
    Âł
    -0.70
     cunt
    -0.69
     ;)
    -0.68
    Firstly
    -0.67
    Ùĩ
    -0.66
     negro
    -0.66
    ↵Âł
    -0.64
     Whilst
    -0.64
    POSITIVE LOGITS
     POLITICO
    0.86
     spokeswoman
    0.84
     lawmakers
    0.79
     spokesman
    0.75
     HuffPost
    0.72
     lawmaker
    0.71
     federal
    0.65
     automakers
    0.64
     Tillerson
    0.64
     Obama
    0.64
    Activations Density 1.620%

    No Known Activations