© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 13726
    Prev
    Next
    INDEX
    Explanations

    declarative statements about events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce or refer to significant statements or events

    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
     Lovecraft
    -0.68
     fandom
    -0.65
    cellence
    -0.63
    ãĤ¦ãĤ¹
    -0.63
     Dungeons
    -0.62
    ģĸ
    -0.60
     Ashes
    -0.60
    ̶
    -0.60
     Graveyard
    -0.60
     Divinity
    -0.60
    POSITIVE LOGITS
     spokeswoman
    0.91
     spokesman
    0.84
    ogether
    0.78
     later
    0.73
     also
    0.72
    sequently
    0.72
     latter
    0.72
     subsequently
    0.71
     Leilan
    0.71
     additionally
    0.70
    Activations Density 0.582%

    No Known Activations