© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1479
    Prev
    Next
    INDEX
    Explanations

    details or descriptions related to historical events or figures

    oai_token-act-pair · gpt-3.5-turbo

    references to significant historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rils
    -0.78
    roth
    -0.73
    alg
    -0.71
     yuan
    -0.69
    Ability
    -0.68
    ħĭ
    -0.67
    optional
    -0.66
    Apply
    -0.65
    ango
    -0.65
     Aura
    -0.64
    POSITIVE LOGITS
     1917
    0.89
     childhood
    0.88
     eras
    0.86
     1977
    0.86
     1916
    0.83
    ewitness
    0.82
     1963
    0.82
     era
    0.81
     1914
    0.81
     1947
    0.80
    Activations Density 1.361%

    No Known Activations