© 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. 2-RES-JB
    11. 12814
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Seminole tribe

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Semin" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åº
    -0.73
    TW
    -0.69
    theless
    -0.69
    draw
    -0.68
    å¼
    -0.68
    SIZE
    -0.66
    century
    -0.66
    susp
    -0.65
    çĦ
    -0.65
    dress
    -0.65
    POSITIVE LOGITS
    adoes
    1.01
     Semin
    0.98
    flation
    0.88
    agin
    0.88
    ines
    0.85
    oles
    0.84
    idia
    0.83
    emonium
    0.80
    outher
    0.76
     opio
    0.75
    Activations Density 0.017%

    No Known Activations