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. 1632
    Prev
    Next
    INDEX
    Explanations

    instances where there are specific criteria or conditions being discussed

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to statistical analysis and distribution

    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
    Ĥİ
    -0.64
    jen
    -0.57
    POST
    -0.56
    steps
    -0.53
    late
    -0.53
    WARD
    -0.53
    cakes
    -0.52
    Monitor
    -0.52
    HAEL
    -0.52
    Journal
    -0.51
    POSITIVE LOGITS
     knack
    0.71
     overlap
    0.68
     spare
    0.62
     flair
    0.61
     sway
    0.59
     capability
    0.59
     chance
    0.58
     overlapping
    0.58
     clout
    0.57
     resemb
    0.57
    Activations Density 0.964%

    No Known Activations