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. 0-RES-JB
    6. 5537
    Prev
    Next
    INDEX
    Explanations

    phrases related to agreement or consent

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "conc" and its variations, likely related to "concurrence" or "concussion."

    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
    unia
    -0.83
    arget
    -0.71
    dark
    -0.71
    ataka
    -0.68
     OG
    -0.67
    BILITIES
    -0.67
     Thief
    -0.66
     Logged
    -0.66
    fed
    -0.65
     outfit
    -0.64
    POSITIVE LOGITS
     conc
    4.08
     Conc
    2.49
     dissenting
    1.22
     reconc
    1.18
     concussion
    1.09
     concurrent
    1.02
     CONC
    1.01
     cons
    0.95
     interchange
    0.93
     dissent
    0.92
    Activations Density 0.022%

    No Known Activations