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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6511
    Prev
    Next
    INDEX
    Explanations

    phrases related to fleeing or escaping from a location or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to escaping or fleeing from situations

    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
    soDeliveryDate
    -1.01
    Boost
    -0.76
     Tradable
    -0.73
    çĶ°
    -0.72
    natureconservancy
    -0.70
    yi
    -0.69
    wcs
    -0.69
    Yu
    -0.68
    uliffe
    -0.66
    okia
    -0.65
    POSITIVE LOGITS
     clut
    1.04
     confines
    0.91
     wreckage
    0.84
     wrath
    0.81
     rav
    0.76
     wilderness
    0.76
     captivity
    0.75
     collapsing
    0.75
     blaze
    0.75
     heights
    0.75
    Activations Density 0.169%

    No Known Activations