© 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 EvalsExportsinterp-engineNEWAPI 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. 2-RES-JB
    11. 13051
    Prev
    Next
    INDEX
    Explanations

    instances where a specific franchise or brand is mentioned

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sports team leadership or key players

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Reviewer
    -0.82
    IAS
    -0.76
     execution
    -0.69
    iam
    -0.69
    ensor
    -0.69
    ESSION
    -0.66
     culp
    -0.63
    Frameworks
    -0.63
    iple
    -0.63
    IME
    -0.63
    POSITIVE LOGITS
     Occupations
    0.77
     Trees
    0.74
     kWh
    0.74
     pts
    0.71
     CET
    0.67
     Khe
    0.66
     Generations
    0.65
    ãĤ©
    0.65
     yr
    0.64
    yll
    0.61
    Activations Density 0.000%

    No Known Activations