© 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. 3-RES-JB
    11. 616
    Prev
    Next
    INDEX
    Explanations

    names or terms related to political figures or entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the organization of entities, such as levels or rankings associated with 'Os' and 'Gs'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ©
    -0.85
    ãĤ¡
    -0.83
    ãĥ¼ãĥĨãĤ£
    -0.75
    ONSORED
    -0.75
    theless
    -0.74
    ++++
    -0.71
    âĢ¢âĢ¢
    -0.70
    sburgh
    -0.70
     grounds
    -0.69
    Charl
    -0.63
    POSITIVE LOGITS
    hiba
    0.97
    igmatic
    0.95
    wered
    0.92
    mith
    0.91
    ilon
    0.89
    ugi
    0.87
    ophical
    0.85
    boro
    0.85
    sterdam
    0.82
    ols
    0.80
    Activations Density 0.008%

    No Known Activations