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. 6-RES-JB
    6. 2097
    Prev
    Next
    INDEX
    Explanations

    phrases indicating alternative or additional names for entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate alternative names or designations for something

    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
    ftime
    -0.76
    iscal
    -0.71
    uble
    -0.69
    erity
    -0.67
    pled
    -0.66
     Rasmussen
    -0.65
    pering
    -0.65
    avorite
    -0.63
    efficiency
    -0.63
    users
    -0.63
    POSITIVE LOGITS
     Occupations
    0.80
    ãĤī
    0.76
     اÙĦ
    0.73
    л
    0.72
    м
    0.69
     ans
    0.69
    å·
    0.68
    inez
    0.68
    poons
    0.65
     è£ıç
    0.65
    Activations Density 0.064%

    No Known Activations