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. 21494
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Spring"

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "Spring."

    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
    iasis
    -0.72
    İĭ
    -0.72
    anyahu
    -0.69
    phabet
    -0.69
    ittees
    -0.67
     looph
    -0.65
    ittee
    -0.64
    iciary
    -0.64
     scrolling
    -0.64
     teasp
    -0.64
    POSITIVE LOGITS
    steen
    1.20
    dale
    1.06
    trap
    1.03
    meier
    0.93
     Arbor
    0.91
    brook
    0.89
    mary
    0.88
    ween
    0.86
    forest
    0.84
    field
    0.82
    Activations Density 0.009%

    No Known Activations