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. 9-RES-JB
    6. 781
    Prev
    Next
    INDEX
    Explanations

    terms related to specific actions or events in a professional or organizational context, such as freezing hiring, staffing, finances, or bonuses

    oai_token-act-pair · gpt-3.5-turbo

    topics related to societal issues and personal circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     alike
    -0.60
     Sect
    -0.58
    ggles
    -0.57
    nant
    -0.55
    asms
    -0.53
    humans
    -0.52
    iverse
    -0.47
    phant
    -0.47
    gger
    -0.47
     greatness
    -0.47
    POSITIVE LOGITS
     and
    0.79
     or
    0.73
     &
    0.60
    pection
    0.57
    staking
    0.56
    creen
    0.55
     respons
    0.54
     identifying
    0.53
    / 
    0.53
     "$:/
    0.52
    Activations Density 1.280%

    No Known Activations