© 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. 9586
    Prev
    Next
    INDEX
    Explanations

    financial figures and currency symbols

    oai_token-act-pair · gpt-3.5-turbo
    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
     Ange
    -0.70
    ktop
    -0.67
     Underground
    -0.67
     Printing
    -0.66
     Bend
    -0.62
     drafts
    -0.61
     Icar
    -0.59
     Tire
    -0.59
     sketch
    -0.58
     SET
    -0.57
    POSITIVE LOGITS
    29
    1.00
    69
    0.99
    39
    0.99
    89
    0.98
    24
    0.98
    49
    0.97
    119
    0.96
    79
    0.96
    28
    0.95
     39
    0.95
    Activations Density 0.177%

    No Known Activations