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

    Neuronpedia

    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. 19156
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "az" along with associated numbers

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the string 'az' in various contexts

    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
    ACTED
    -0.72
     foremost
    -0.65
     Fargo
    -0.64
     Impossible
    -0.62
     Seah
    -0.59
    ritional
    -0.59
    perature
    -0.58
    itures
    -0.58
     Carolina
    -0.57
     fixme
    -0.56
    POSITIVE LOGITS
    hou
    1.11
    ombie
    1.07
    arro
    0.97
    hang
    0.93
    quez
    0.90
    hur
    0.89
     Sharif
    0.89
    awa
    0.86
    eez
    0.86
    ombies
    0.84
    Activations Density 0.037%

    No Known Activations