© 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. 3-RES-JB
    11. 10628
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or political manipulation of the masses

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people

    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
    tein
    -1.05
    cer
    -0.76
    Acknowled
    -0.72
    ces
    -0.71
     Nig
    -0.65
    Chain
    -0.63
    mingham
    -0.63
    chron
    -0.62
    Else
    -0.62
    NER
    -0.61
    POSITIVE LOGITS
     masses
    0.92
    ourcing
    0.86
    rake
    0.82
    hare
    0.81
    hari
    0.75
    urch
    0.74
    aic
    0.74
    ourced
    0.73
    ongs
    0.73
    ayers
    0.72
    Activations Density 0.015%

    No Known Activations