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. 10-RES-JB
    6. 20303
    Prev
    Next
    INDEX
    Explanations

    words related to events or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various types of musical or performance expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Raw
    -0.74
     Accountability
    -0.74
     Allies
    -0.72
     Ethics
    -0.72
     Right
    -0.70
     Freedom
    -0.69
     Legacy
    -0.67
     Enterprise
    -0.65
     Hitman
    -0.64
     Founders
    -0.64
    POSITIVE LOGITS
    aned
    1.13
    anus
    1.11
    ework
    1.04
    idium
    1.04
    lest
    1.04
    onal
    1.03
    olis
    1.03
    illions
    1.02
    ril
    1.02
    amen
    1.01
    Activations Density 0.265%

    No Known Activations