© 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. 17338
    Prev
    Next
    INDEX
    Explanations

    words related to causing an impact or effect, whether positive or negative

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to causing significant reactions or consequences

    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
     sugg
    -0.75
    lished
    -0.71
     Provided
    -0.69
    provided
    -0.67
    ¥µ
    -0.64
    razen
    -0.63
    uthor
    -0.63
    Õ
    -0.63
     provided
    -0.62
     Tactics
    -0.62
    POSITIVE LOGITS
     havoc
    1.16
     disturbance
    0.91
     headaches
    0.90
     damage
    0.85
     unnecessary
    0.85
     harm
    0.83
     mayhem
    0.81
     wedge
    0.79
     wrath
    0.78
     uproar
    0.76
    Activations Density 0.114%

    No Known Activations