© 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. 6-RES-JB
    11. 20745
    Prev
    Next
    INDEX
    Explanations

    sentences where actions or events are being described

    oai_token-act-pair · gpt-3.5-turbo

    key elements in legal and relational contexts, particularly focusing on sources and references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scient
    -0.66
     ration
    -0.63
    efer
    -0.60
    of
    -0.59
     Whitman
    -0.59
     interstate
    -0.58
     stimulus
    -0.57
     pronoun
    -0.57
     myster
    -0.57
     exits
    -0.56
    POSITIVE LOGITS
    è£ħ
    1.00
    ombat
    0.91
    yip
    0.91
     dstg
    0.85
    soDeliveryDate
    0.84
    SourceFile
    0.83
    ãĤ¦ãĤ¹
    0.82
    £ı
    0.81
    ĵĺ
    0.79
     guiActiveUn
    0.79
    Activations Density 0.648%

    No Known Activations