© 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. 3111
    Prev
    Next
    INDEX
    Explanations

    dates and birthplaces of individuals, especially actors and actresses

    oai_token-act-pair · gpt-3.5-turbo

    birth dates and ages of individuals

    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
    ighting
    -0.78
    ħĭ
    -0.70
    isoft
    -0.69
    uliffe
    -0.67
    GW
    -0.67
    consumer
    -0.67
    fights
    -0.66
    defense
    -0.66
    nox
    -0.66
    Plug
    -0.66
    POSITIVE LOGITS
     1946
    0.85
     1961
    0.83
     1952
    0.82
     1928
    0.82
     1924
    0.80
     1959
    0.80
     1932
    0.77
     surname
    0.77
     daughter
    0.76
     1921
    0.76
    Activations Density 0.111%

    No Known Activations