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. 22202
    Prev
    Next
    INDEX
    Explanations

    phrases related to news articles or report titles

    oai_token-act-pair · gpt-3.5-turbo

    formatting elements and structural components within the text

    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
     Samar
    -0.77
    leans
    -0.73
     Plane
    -0.71
    DERR
    -0.67
    ĪĴ
    -0.67
    ministic
    -0.66
    milo
    -0.63
    pora
    -0.59
     Parables
    -0.59
    ernel
    -0.58
    POSITIVE LOGITS
    ]"
    1.02
    ]
    0.96
    ][/
    0.91
    quote
    0.89
    inline
    0.87
    =]
    0.86
    ][
    0.84
    %]
    0.84
    gallery
    0.80
    "]=>
    0.78
    Activations Density 0.064%

    No Known Activations