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. 15984
    Prev
    Next
    INDEX
    Explanations

    mentions of something having a strong impact or influence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the special character "âĢ" and its various contexts in the text

    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
     RAD
    -0.68
     detached
    -0.63
     charm
    -0.63
     decomp
    -0.63
     Somerset
    -0.62
     sled
    -0.62
     cottage
    -0.61
     recording
    -0.61
    ctors
    -0.60
     coast
    -0.58
    POSITIVE LOGITS
    ¬
    1.05
    catentry
    0.93
    âĢł
    0.92
    ¡
    0.89
    ¾
    0.89
    ¢
    0.88
    £
    0.87
    _.
    0.85
    Â
    0.85
    Ĵ
    0.84
    Activations Density 0.387%

    No Known Activations