© 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. 8-RES-JB
    11. 7237
    Prev
    Next
    INDEX
    Explanations

    instances of talk about cutting or providing financial support

    oai_token-act-pair · gpt-3.5-turbo

    terms related to funding and financial support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACTED
    -0.63
    uzzle
    -0.63
    appropriate
    -0.59
    obl
    -0.59
    ipher
    -0.58
    positive
    -0.58
    PRES
    -0.57
    othermal
    -0.57
    Rand
    -0.57
    oscopic
    -0.55
    POSITIVE LOGITS
     altogether
    1.77
     entirely
    1.20
     prematurely
    1.09
     indefinitely
    1.01
     abruptly
    0.99
     due
    0.95
     inhib
    0.93
     outright
    0.92
     because
    0.85
     citing
    0.83
    Activations Density 0.541%

    No Known Activations