© 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. 3-RES-JB
    11. 6445
    Prev
    Next
    INDEX
    Explanations

    references to the Department of Veterans Affairs

    oai_token-act-pair · gpt-3.5-turbo

    references to Veterans Affairs and related organizations or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    liness
    -0.76
    arb
    -0.74
    bender
    -0.72
    abl
    -0.71
    gered
    -0.71
    dds
    -0.69
    fm
    -0.69
    erb
    -0.69
    zzle
    -0.67
    liest
    -0.66
    POSITIVE LOGITS
     Veterans
    1.24
     Affairs
    1.05
     Veteran
    0.98
     Memorial
    0.96
     Benefits
    0.96
     Remem
    0.87
     Rehab
    0.86
    Veter
    0.85
     Reserve
    0.85
     Sym
    0.78
    Activations Density 0.011%

    No Known Activations