© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 6388
    Prev
    Next
    INDEX
    Explanations

    mentions of events or occurrences happening in various locations or regions (specifically related to countries)

    oai_token-act-pair · gpt-3.5-turbo

    references to protests or significant events happening nationwide

    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
    illus
    -0.75
    Module
    -0.70
    bol
    -0.69
    ogens
    -0.68
    SourceFile
    -0.68
    imon
    -0.67
    PO
    -0.67
    thood
    -0.67
    char
    -0.66
     Priv
    -0.65
    POSITIVE LOGITS
     skyline
    0.79
     converge
    0.78
     campuses
    0.74
     conver
    0.73
    wide
    0.73
     spotlight
    0.66
     carriers
    0.66
    arcer
    0.66
     alike
    0.63
     illegally
    0.63
    Activations Density 0.086%

    No Known Activations