© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 11437
    Prev
    Next
    INDEX
    Explanations

    phrases related to goals or objectives in a document

    oai_token-act-pair · gpt-3.5-turbo

    phrases and structures that indicate objectives or purposes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isms
    -0.80
    rimp
    -0.71
    dayName
    -0.70
    aults
    -0.70
    rums
    -0.69
    case
    -0.69
    ashtra
    -0.67
    leep
    -0.67
    iaries
    -0.66
    rings
    -0.64
    POSITIVE LOGITS
     this
    0.79
     constructing
    0.77
     these
    0.74
    ENTION
    0.71
     Operation
    0.71
     combating
    0.70
     determining
    0.69
     preserving
    0.69
     establishing
    0.69
     policing
    0.68
    Activations Density 0.133%

    No Known Activations