© 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. 13380
    Prev
    Next
    INDEX
    Explanations

    phrases related to the location of an event or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or contexts within a nation or organization

    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
    onna
    -0.67
     Uriel
    -0.63
    gery
    -0.61
    agascar
    -0.61
     viol
    -0.60
     Taxes
    -0.60
     ahead
    -0.60
    rex
    -0.59
     torches
    -0.58
    vu
    -0.58
    POSITIVE LOGITS
     confines
    1.68
     bounds
    1.45
     boundaries
    1.23
     limits
    1.11
     parameters
    1.08
     borders
    1.04
     scope
    1.00
     constraints
    0.94
     realm
    0.93
     radius
    0.93
    Activations Density 0.089%

    No Known Activations