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

    Neuronpedia

    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. 4-RES-JB
    11. 2188
    Prev
    Next
    INDEX
    Explanations

    words related to financial support or funding

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial support and oversight in various contexts

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

    No Comments

    Negative Logits
    WER
    -0.90
     Rite
    -0.72
     Royale
    -0.72
    GROUND
    -0.72
     Summit
    -0.70
    Failure
    -0.69
    ocene
    -0.68
     Sense
    -0.68
    Reply
    -0.68
     resemblance
    -0.67
    POSITIVE LOGITS
    inated
    1.26
    inating
    1.15
    imated
    1.12
    inate
    1.10
    ised
    1.04
    inations
    1.02
    ories
    0.98
    izing
    0.98
    ization
    0.97
    inates
    0.97
    Activations Density 0.026%

    No Known Activations