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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 20838
    Prev
    Next
    INDEX
    Explanations

    words related to specific names and terms like "Ja", "JP", "Jin", "JC", "JA", "Jes", and "J" occurring with varying activation strengths

    oai_token-act-pair · gpt-3.5-turbo

    the presence of blank tokens or separators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    holders
    -1.04
    holder
    -0.76
    mble
    -0.68
    itures
    -0.66
    erness
    -0.64
    ifiers
    -0.64
    igating
    -0.64
    rums
    -0.61
     constit
    -0.61
     thirds
    -0.60
    POSITIVE LOGITS
    unction
    1.10
    oint
    1.04
    ealous
    1.03
    upiter
    1.01
    igsaw
    0.94
    ournals
    0.91
    utsu
    0.89
    ansen
    0.86
    ordan
    0.85
    ataka
    0.83
    Activations Density 0.105%

    No Known Activations