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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 5-RES-JB
    6. 16146
    Prev
    Next
    INDEX
    Explanations

    specific numerical and symbol patterns

    oai_token-act-pair · gpt-3.5-turbo

    various numerical or coded data elements, possibly related to sports statistics or event timestamps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toget
    -0.69
     veins
    -0.67
     faithfully
    -0.61
     ingred
    -0.61
     proport
    -0.60
     Brach
    -0.60
     amounted
    -0.59
     convol
    -0.58
     once
    -0.58
     wholes
    -0.58
    POSITIVE LOGITS
    anyahu
    0.80
    meier
    0.74
    Interstitial
    0.70
    aniel
    0.70
    avez
    0.68
    cation
    0.67
     Narr
    0.67
    0200
    0.67
    ACTED
    0.65
    omsky
    0.65
    Activations Density 0.138%

    No Known Activations