Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 8951
    Prev
    Next
    INDEX
    Explanations

    punctuated sentences and statements

    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 @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     volunte
    -0.63
     neighb
    -0.62
     earthqu
    -0.57
     surrendered
    -0.56
     subur
    -0.53
     targeted
    -0.52
     screened
    -0.52
     ineligible
    -0.51
    iliated
    -0.50
     carbohyd
    -0.50
    POSITIVE LOGITS
     Suppose
    1.00
    Firstly
    0.93
     Firstly
    0.91
     Anyway
    0.82
    Anyway
    0.80
     Basically
    0.78
     Whilst
    0.76
    Secondly
    0.75
     Secondly
    0.74
    Consider
    0.72
    Activations Density 0.556%

    No Known Activations