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. 22420
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to actions or events in sports

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "âĢ" in various contexts within 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
     scattering
    -0.75
     infringing
    -0.71
     tremend
    -0.67
     variance
    -0.65
     dividing
    -0.64
    romy
    -0.63
     cyan
    -0.62
     handshake
    -0.60
     shack
    -0.60
     crossover
    -0.58
    POSITIVE LOGITS
    ¹
    1.08
    £
    1.07
    º
    1.01
    ł
    0.93
    ¡
    0.92
    Ĵ
    0.91
    ¬
    0.89
    ¸
    0.89
    ħ
    0.88
    Ń
    0.87
    Activations Density 0.215%

    No Known Activations