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. 2-RES-JB
    6. 18024
    Prev
    Next
    INDEX
    Explanations

    terms related to anatomy

    oai_token-act-pair · gpt-3.5-turbo

    terms related to anatomy and anatomical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vous
    -0.79
    invoke
    -0.73
    fleet
    -0.72
    wagen
    -0.71
    quote
    -0.66
    Leary
    -0.64
    0002
    -0.64
    ãģ®éŃĶ
    -0.64
     Millennium
    -0.64
    government
    -0.63
    POSITIVE LOGITS
    omical
    1.12
    omy
    1.06
     Anat
    0.99
     anat
    0.96
     disse
    0.94
    MpServer
    0.88
    alys
    0.84
    emy
    0.82
    olit
    0.82
    olia
    0.78
    Activations Density 0.014%

    No Known Activations