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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-RES-JB
    6. 7637
    Prev
    Next
    INDEX
    Explanations

    situations where a number is associated with an ordinal position

    oai_token-act-pair · gpt-3.5-turbo

    numerical indicators of sequences or rankings related to seasons and achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    details
    -0.80
    ITNESS
    -0.76
    rez
    -0.68
    Attributes
    -0.67
    ppings
    -0.66
    blers
    -0.66
    stones
    -0.66
    Images
    -0.65
    kens
    -0.65
    bara
    -0.65
    POSITIVE LOGITS
     consecutive
    1.55
     straight
    1.19
     anniversary
    1.16
    straight
    1.13
     successive
    1.09
     birthday
    1.09
     Anniversary
    1.00
    iversary
    0.87
     year
    0.84
     Birthday
    0.84
    Activations Density 0.060%

    No Known Activations