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. 8-RES-JB
    6. 5148
    Prev
    Next
    INDEX
    Explanations

    items related to personal care and grooming

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or characters, particularly those that start with "Az."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.69
    perature
    -0.63
     Fargo
    -0.62
    ritional
    -0.61
     foremost
    -0.59
     Impossible
    -0.58
     Seah
    -0.58
    ATURE
    -0.57
     Carolina
    -0.56
    erest
    -0.56
    POSITIVE LOGITS
    ombie
    1.12
    hou
    1.04
    quez
    0.96
     Sharif
    0.89
    hur
    0.88
    eez
    0.87
    ombies
    0.85
    hang
    0.85
    arro
    0.82
    hi
    0.80
    Activations Density 0.040%

    No Known Activations