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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 6-RES-JB
    11. 13901
    Prev
    Next
    INDEX
    Explanations

    terms related to being driven or oriented towards a specific goal or focus

    oai_token-act-pair · gpt-3.5-turbo

    terms related to being driven or oriented towards specific goals or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.77
    Said
    -0.74
    arthy
    -0.73
    ricanes
    -0.73
    oother
    -0.71
    IFIED
    -0.69
    kar
    -0.69
    irl
    -0.68
    ylum
    -0.68
    Used
    -0.68
    POSITIVE LOGITS
     approach
    0.99
     mindset
    0.88
     attitude
    0.88
     fashion
    0.86
     behavior
    0.85
     policing
    0.83
     behaviour
    0.82
     strategies
    0.81
     attitudes
    0.81
     mentality
    0.80
    Activations Density 0.066%

    No Known Activations