© 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. 12526
    Prev
    Next
    INDEX
    Explanations

    phrases related to the purchase and acquisition of items

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating sources or points of origin

    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
    onential
    -0.81
    struction
    -0.75
    ŃĶ
    -0.70
    ãĥİ
    -0.69
    endiary
    -0.68
    igure
    -0.66
    acterial
    -0.66
     ushered
    -0.64
    bowl
    -0.64
    het
    -0.63
    POSITIVE LOGITS
     reputable
    1.24
     another
    1.08
     abroad
    1.04
     someone
    1.02
     somebody
    1.00
     trusted
    0.98
     trustworthy
    0.97
     anywhere
    0.96
     whichever
    0.95
     elsewhere
    0.92
    Activations Density 0.269%

    No Known Activations