© 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. 2-RES-JB
    11. 19761
    Prev
    Next
    INDEX
    Explanations

    financial terms related to funding or budgeting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial and operational challenges

    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
    Cru
    -0.72
    oak
    -0.68
    atom
    -0.65
    asters
    -0.64
    obby
    -0.63
    NetMessage
    -0.63
    ribing
    -0.63
    Mur
    -0.60
    agog
    -0.59
    uay
    -0.59
    POSITIVE LOGITS
     shortfall
    1.09
    xual
    0.87
     plag
    0.83
     thereof
    0.78
     disproportion
    0.75
     Boko
    0.73
    atile
    0.73
     orphans
    0.73
    nces
    0.72
     defic
    0.70
    Activations Density 0.010%

    No Known Activations