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. 10-RES-JB
    6. 8868
    Prev
    Next
    INDEX
    Explanations

    metadata related to editing

    oai_token-act-pair · gpt-3.5-turbo

    brackets or references to sections within a list or documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comprom
    -0.80
     eleph
    -0.78
    everal
    -0.76
     oun
    -0.72
     conduc
    -0.71
     misunder
    -0.71
     occas
    -0.69
     thous
    -0.68
    '';
    -0.65
     gobl
    -0.65
    POSITIVE LOGITS
     edit
    1.86
     Edit
    1.56
    ?]
    1.27
    edit
    1.22
    ][
    1.14
     ]
    1.08
    ¶
    1.08
     citation
    1.01
    Edit
    0.96
     ][
    0.92
    Activations Density 0.009%

    No Known Activations