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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12729
    Prev
    Next
    INDEX
    Explanations

    high-ranking titles or positions in an organization

    oai_token-act-pair · gpt-3.5-turbo

    instances of the abbreviation 'HR', likely referring to human rights

    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
    Not in Any Lists

    No Comments

    Negative Logits
     cent
    -0.66
     Mane
    -0.65
     ens
    -0.64
     buildup
    -0.63
     Canary
    -0.63
     edges
    -0.62
     Charles
    -0.62
    coni
    -0.62
     mutants
    -0.61
     tw
    -0.61
    POSITIVE LOGITS
    HR
    4.52
     HR
    2.41
    hr
    1.84
    HB
    1.62
    HCR
    1.43
    HL
    1.41
    HI
    1.40
     hr
    1.37
    HH
    1.36
    HER
    1.29
    Activations Density 0.009%

    No Known Activations