© 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. 23403
    Prev
    Next
    INDEX
    Explanations

    words related to various types of physical and mental health issues, such as cancer, blood extraction, and medical treatments

    oai_token-act-pair · gpt-3.5-turbo

    terms related to financial burdens and expenses

    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
     guiActiveUn
    -0.64
    ngth
    -0.63
     Fired
    -0.62
    ãĥ¯ãĥ³
    -0.60
     JPM
    -0.60
    izabeth
    -0.60
    VIS
    -0.59
     Remastered
    -0.59
     Celebrity
    -0.59
    xual
    -0.58
    POSITIVE LOGITS
    levard
    0.95
    ylon
    0.81
    keyes
    0.80
    ecause
    0.76
    ucha
    0.72
    kered
    0.72
    anc
    0.71
    legged
    0.70
    erville
    0.70
    ishment
    0.70
    Activations Density 0.112%

    No Known Activations