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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 3363
    Prev
    Next
    INDEX
    Explanations

    sentences that emphasize the importance or impact of a particular person or action

    oai_token-act-pair · gpt-3.5-turbo

    sentences that express conclusive statements or remarks

    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
     encl
    -0.89
     autonom
    -0.86
     authorised
    -0.80
     censored
    -0.79
     enclosed
    -0.77
     vegetarian
    -0.76
    riet
    -0.76
     behaviour
    -0.75
     anthrop
    -0.75
     compulsory
    -0.74
    POSITIVE LOGITS
     Granted
    1.38
     Regardless
    1.22
     Considering
    1.17
     Hopefully
    1.15
     Especially
    1.15
     Expect
    1.14
     Additionally
    1.13
     Obviously
    1.12
     Unfortunately
    1.11
     Conversely
    1.10
    Activations Density 0.366%

    No Known Activations