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. 23769
    Prev
    Next
    INDEX
    Explanations

    words related to significant negative events or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "devastating" and related negative impacts

    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
    cius
    -0.88
    ploma
    -0.77
    cling
    -0.68
    annis
    -0.67
    ioch
    -0.64
    uties
    -0.64
    uni
    -0.63
    walk
    -0.62
    endment
    -0.62
    Ĭ±
    -0.62
    POSITIVE LOGITS
    ly
    1.10
     blow
    0.99
     havoc
    0.98
     devast
    0.85
    ãĥ¼ãĥĨ
    0.82
     blows
    0.82
     devastation
    0.80
    LY
    0.77
     absor
    0.76
     wrought
    0.75
    Activations Density 0.021%

    No Known Activations