Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 8-RES-JB
    6. 3677
    Prev
    Next
    INDEX
    Explanations

    phrases related to particles and antiparticles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to antimatter and its interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DEN
    -0.77
    Reviewer
    -0.76
    REDACTED
    -0.73
     Duchess
    -0.71
    ãģ®éŃĶ
    -0.68
    âĸ¬âĸ¬
    -0.68
     Cinnamon
    -0.66
     Dag
    -0.64
    ged
    -0.63
    Tonight
    -0.62
    POSITIVE LOGITS
    olitics
    1.15
    ension
    1.12
    rop
    1.12
    racted
    1.10
    agic
    1.09
    olitical
    1.08
    ract
    1.07
    unct
    1.06
    resent
    1.06
    ensive
    1.03
    Activations Density 0.079%

    No Known Activations