© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14104
    Prev
    Next
    INDEX
    Explanations

    words related to medical conditions involving some sort of pit, such as decrepit or heart palpitations

    oai_token-act-pair · gpt-3.5-turbo

    references to "pits" or "pit" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģĦ
    -0.72
    é¾
    -0.70
     Balance
    -0.66
    hips
    -0.63
    æĥ
    -0.62
    lean
    -0.62
    erry
    -0.62
     Congratulations
    -0.60
    Jump
    -0.60
     Flow
    -0.60
    POSITIVE LOGITS
    pit
    0.97
    cher
    0.95
    roleum
    0.95
    chers
    0.83
    ernal
    0.82
    iless
    0.79
    aque
    0.77
    ting
    0.77
    ghazi
    0.74
    hesda
    0.74
    Activations Density 0.012%

    No Known Activations