© 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. 8-RES-JB
    11. 3058
    Prev
    Next
    INDEX
    Explanations

    professionals or experts in various fields

    oai_token-act-pair · gpt-3.5-turbo

    references to experts or authority figures in various fields

    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
    etition
    -0.72
    nih
    -0.69
    tu
    -0.67
    rity
    -0.66
    umo
    -0.64
    imester
    -0.64
    flix
    -0.64
    iasm
    -0.63
    rez
    -0.63
    query
    -0.63
    POSITIVE LOGITS
     extraord
    0.96
     proponent
    0.90
     alike
    0.87
     scourge
    0.86
     contributor
    0.85
     holder
    0.84
     supporter
    0.84
     founding
    0.83
     protector
    0.83
     collaborator
    0.82
    Activations Density 0.242%

    No Known Activations