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. 7-RES-JB
    6. 8401
    Prev
    Next
    INDEX
    Explanations

    mentions of age groups typically in their 20s, 30s, and 40s

    oai_token-act-pair · gpt-3.5-turbo

    references to age, particularly in relation to decades (20s, 30s, 40s, etc.)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Root
    -0.76
    Grab
    -0.70
    edIn
    -0.68
    Pand
    -0.67
    sub
    -0.65
    Owner
    -0.64
    ="#
    -0.64
    tap
    -0.64
     strutConnector
    -0.62
    Unity
    -0.62
    POSITIVE LOGITS
    ixties
    0.87
    idia
    0.87
    omething
    0.77
    cent
    0.76
    omet
    0.75
    ources
    0.75
    isode
    0.72
     percentile
    0.72
    olutions
    0.72
    ighters
    0.71
    Activations Density 0.040%

    No Known Activations