© 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. 10-RES-JB
    11. 16075
    Prev
    Next
    INDEX
    Explanations

    phrases related to likelihood or potentiality

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing perceptions or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilts
    -0.76
    zb
    -0.76
    estern
    -0.75
    ffen
    -0.71
    ainers
    -0.70
    cised
    -0.66
    ogi
    -0.65
    opers
    -0.65
    ests
    -0.64
    ourse
    -0.62
    POSITIVE LOGITS
     innocuous
    1.03
     awfully
    1.03
     oddly
    0.98
     destined
    0.93
     strangely
    0.93
     unlikely
    0.92
     tailor
    0.91
     unstoppable
    0.91
     to
    0.90
     harmless
    0.90
    Activations Density 0.061%

    No Known Activations