© 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. 4-RES-JB
    11. 7289
    Prev
    Next
    INDEX
    Explanations

    words related to geological features and materials

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases associated with various types of structures or categories

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

    No Comments

    Negative Logits
    ħĭ
    -0.81
    ĪĴ
    -0.71
     Eug
    -0.65
     deadline
    -0.61
     rupture
    -0.60
     reconciliation
    -0.59
    ĸļ
    -0.58
     reconcil
    -0.58
     Frederick
    -0.58
     enactment
    -0.57
    POSITIVE LOGITS
    ierrez
    0.94
    grain
    0.78
    abytes
    0.77
    illions
    0.77
    thood
    0.76
    reau
    0.71
    artifacts
    0.70
    soever
    0.69
    esome
    0.68
    orno
    0.65
    Activations Density 0.072%

    No Known Activations