© 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. 21297
    Prev
    Next
    INDEX
    Explanations

    references to the Federal Reserve (Fed) along with associated terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    references to the Federal Reserve

    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
     Faw
    -0.79
     Flavoring
    -0.72
     Carbuncle
    -0.71
    Ô
    -0.69
    lihood
    -0.69
     Monstrous
    -0.66
     Bucc
    -0.66
    ______
    -0.65
     Lebanese
    -0.65
    ··
    -0.64
    POSITIVE LOGITS
    erer
    1.14
    oras
    1.00
    ERAL
    0.95
    rik
    0.95
    ric
    0.92
    ricular
    0.92
    eli
    0.91
    ered
    0.91
    rique
    0.89
    rix
    0.88
    Activations Density 0.010%

    No Known Activations