© 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. 0-RES-JB
    11. 1068
    Prev
    Next
    INDEX
    Explanations

    dates presented in the format 'YYYY'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific historical years

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •Embedding Space Digit Features

    No Comments

    Negative Logits
    Ke
    -0.76
     Jac
    -0.69
    gem
    -0.69
    Jac
    -0.66
    jc
    -0.65
    CT
    -0.64
     reins
    -0.64
    KE
    -0.64
     tap
    -0.63
    ig
    -0.62
    POSITIVE LOGITS
     1942
    2.51
     1941
    2.37
     1943
    2.09
     1944
    1.41
     1911
    1.37
     1862
    1.33
     1886
    1.31
     1902
    1.25
     1991
    1.24
     1905
    1.20
    Activations Density 0.010%

    No Known Activations