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. 0-RES-JB
    6. 20772
    Prev
    Next
    INDEX
    Explanations

    medical conditions and terms related to procedures and regulations

    oai_token-act-pair · gpt-3.5-turbo

    references to emergencies or urgent situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fal
    -0.62
    opol
    -0.61
     worship
    -0.60
     slaying
    -0.60
     persuasion
    -0.59
     abundance
    -0.59
     polyg
    -0.59
     Mot
    -0.58
     monog
    -0.57
     Poly
    -0.56
    POSITIVE LOGITS
    ER
    3.94
    ERS
    2.51
    ERC
    1.97
    er
    1.96
    ERG
    1.96
    ERO
    1.92
    ERA
    1.86
    ERAL
    1.82
    ERY
    1.81
    ERN
    1.79
    Activations Density 0.014%

    No Known Activations