© 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. 7-RES-JB
    11. 1668
    Prev
    Next
    INDEX
    Explanations

    verbs indicating the action of directing something towards a target or recipient

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "directed" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ylon
    -0.72
    tex
    -0.70
    iders
    -0.65
     STAND
    -0.65
     Breaker
    -0.64
    urity
    -0.64
    iddler
    -0.63
    pton
    -0.62
    inventoryQuantity
    -0.61
     Alive
    -0.61
    POSITIVE LOGITS
    ovie
    1.01
     toward
    0.98
    irection
    0.95
     towards
    0.94
    irect
    0.88
    nance
    0.87
     directed
    0.85
    encing
    0.73
    RECT
    0.73
    eering
    0.73
    Activations Density 0.040%

    No Known Activations