© 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. 1-RES-JB
    6. 9534
    Prev
    Next
    INDEX
    Explanations

    references to the economist and writer Thomas Sowell

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals or groups, particularly in political and economic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cryst
    -0.66
     brut
    -0.66
    antha
    -0.64
    catentry
    -0.63
    AMI
    -0.62
     Lank
    -0.59
    stitial
    -0.59
     transact
    -0.59
     Plex
    -0.59
     vap
    -0.59
    POSITIVE LOGITS
    owell
    1.42
    phrine
    0.92
    pedia
    0.87
    baum
    0.84
    sonian
    0.83
    ennett
    0.81
    ready
    0.79
    jad
    0.74
    Reloaded
    0.74
    robe
    0.73
    Activations Density 0.027%

    No Known Activations