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. 11-RES-JB
    6. 23367
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing people or organizations together for a common purpose

    oai_token-act-pair · gpt-3.5-turbo

    connections between groups and collaboration within communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osterone
    -0.72
     Carnage
    -0.65
    isec
    -0.65
    rarily
    -0.62
    advertising
    -0.62
     Nightmares
    -0.61
     Dragonbound
    -0.61
    ozy
    -0.61
     Massacre
    -0.60
    SpaceEngineers
    -0.58
    POSITIVE LOGITS
     interested
    1.25
     passionate
    1.07
     representing
    1.05
     ranging
    1.02
     specializing
    1.01
     united
    0.96
     spanning
    0.96
     from
    0.96
     collaborating
    0.94
     eager
    0.94
    Activations Density 0.357%

    No Known Activations