© 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. 2-RES-JB
    11. 12465
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a personal belief or understanding

    oai_token-act-pair · gpt-3.5-turbo

    the concept of "impression."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yss
    -0.84
    annis
    -0.81
    regulated
    -0.69
     hips
    -0.68
     contiguous
    -0.65
    seek
    -0.65
    atts
    -0.65
     planning
    -0.65
    moving
    -0.64
     plotted
    -0.64
    POSITIVE LOGITS
     impression
    1.35
     impressions
    1.17
    uren
    0.86
     perceptions
    0.76
    IELD
    0.73
    eless
    0.73
    ãĤ¦ãĤ¹
    0.71
    ually
    0.70
    ãĤ«
    0.69
    izable
    0.68
    Activations Density 0.006%

    No Known Activations