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. 1-RES-JB
    6. 4372
    Prev
    Next
    INDEX
    Explanations

    links for edits or comments in a document

    oai_token-act-pair · gpt-3.5-turbo

    references and citations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesday
    -0.86
    wagen
    -0.83
     occas
    -0.75
     pens
    -0.74
    mable
    -0.70
    edIn
    -0.70
     somew
    -0.69
     seizures
    -0.68
     writ
    -0.67
    monton
    -0.67
    POSITIVE LOGITS
    ?]
    1.26
     edit
    1.14
    ËĪ
    1.07
    !]
    1.07
    %]
    0.97
    Footnote
    0.96
    actionDate
    0.96
    ](
    0.93
     ]
    0.89
    ][
    0.88
    Activations Density 0.035%

    No Known Activations