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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7-RES-JB
    11. 7987
    Prev
    Next
    INDEX
    Explanations

    words related to economic performance and financial actions

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with economic decline and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     captive
    -0.77
     ACTION
    -0.75
     inaction
    -0.74
     unsupported
    -0.74
    Reviewer
    -0.71
    BACK
    -0.68
     inclusive
    -0.67
     paradigm
    -0.67
     sarc
    -0.67
     existential
    -0.67
    POSITIVE LOGITS
    uates
    1.15
    uably
    1.13
    ved
    1.09
    ighed
    1.09
    icably
    1.06
    pped
    1.06
    pling
    1.06
    uously
    1.05
    uated
    1.04
    ited
    1.04
    Activations Density 0.160%

    No Known Activations