© 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. 4-RES-JB
    11. 10284
    Prev
    Next
    INDEX
    Explanations

    phrases related to privacy and environmental issues

    oai_token-act-pair · gpt-3.5-turbo

    terms related to environmental regulations and implications

    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
    sy
    -0.81
    enos
    -0.80
    doms
    -0.69
     motif
    -0.66
    ammy
    -0.66
    hiba
    -0.64
     clans
    -0.64
    atars
    -0.63
    kr
    -0.62
     plag
    -0.61
    POSITIVE LOGITS
    OPA
    0.74
    ategory
    0.68
     Technician
    0.66
     Equality
    0.64
     Entreprene
    0.63
    abe
    0.63
    parency
    0.63
     Antarctic
    0.62
    bestos
    0.62
    anded
    0.62
    Activations Density 0.239%

    No Known Activations