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. 16920
    Prev
    Next
    INDEX
    Explanations

    terms related to simulating or imagining something in a creative context

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "immigrant" and related terms

    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
     imagination
    -0.72
    ²¾
    -0.68
     stakes
    -0.68
    nces
    -0.67
    «ĺ
    -0.66
     geo
    -0.66
    ģĸ
    -0.66
     mileage
    -0.66
    ften
    -0.64
     tilt
    -0.64
    POSITIVE LOGITS
    igrants
    1.38
    imm
    1.28
    ersion
    1.16
    ortal
    1.11
    igrated
    1.10
    ersive
    1.08
    aterial
    1.06
    obil
    1.06
    ovable
    1.06
    igration
    1.05
    Activations Density 0.008%

    No Known Activations