© 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. 0-RES-JB
    6. 23185
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically Malawi

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of a specific name or term associated with influential figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     doom
    -0.71
     particle
    -0.67
     Gravity
    -0.65
     Gentle
    -0.64
     meaningless
    -0.61
     dim
    -0.61
     ticket
    -0.61
     sweet
    -0.59
     Gran
    -0.59
     st
    -0.58
    POSITIVE LOGITS
    awi
    4.65
    ouri
    1.19
    ouf
    1.07
    aji
    1.02
    iman
    1.01
    awa
    1.01
    ani
    0.99
    aw
    0.99
    odox
    0.99
    awan
    0.99
    Activations Density 0.019%

    No Known Activations