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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 13673
    Prev
    Next
    INDEX
    Explanations

    fear or regret related to past events that the individual wishes to avoid in the future

    oai_token-act-pair · gpt-3.5-turbo

    phrases involving the concept of recurrence or repetition

    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
    anooga
    -0.74
    OTS
    -0.69
    SEA
    -0.68
    kees
    -0.67
    emet
    -0.66
    latest
    -0.65
    ometric
    -0.65
    kee
    -0.65
     parap
    -0.64
    HT
    -0.63
    POSITIVE LOGITS
     someday
    0.79
     Dialogue
    0.73
    nir
    0.69
    abil
    0.69
     conclud
    0.69
    atile
    0.69
     Generations
    0.68
    soever
    0.67
     :-)
    0.66
     nostalg
    0.63
    Activations Density 0.024%

    No Known Activations