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. 3702
    Prev
    Next
    INDEX
    Explanations

    words related to a state of neglect or decline

    oai_token-act-pair · gpt-3.5-turbo

    words related to decay or deterioration

    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
    dar
    -0.72
    zyme
    -0.68
    sports
    -0.65
    Hyper
    -0.63
    omes
    -0.62
     Wyatt
    -0.61
    attribute
    -0.61
     intervening
    -0.60
    elson
    -0.59
     Deal
    -0.58
    POSITIVE LOGITS
     langu
    1.16
    pless
    0.82
    ishing
    0.82
    emate
    0.79
    ishable
    0.79
    iously
    0.78
     seiz
    0.77
    ength
    0.77
     strugg
    0.76
    uously
    0.74
    Activations Density 0.009%

    No Known Activations