© 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. 11820
    Prev
    Next
    INDEX
    Explanations

    mentions of efforts to eradicate or minimize something, along with mentions of supporting it

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific subject or issue

    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
     Siege
    -0.67
     Anarchy
    -0.67
     Pirates
    -0.66
     Wheel
    -0.64
    idth
    -0.63
     Balloon
    -0.63
     Nano
    -0.62
     Knife
    -0.62
     Kang
    -0.61
     Yellow
    -0.60
    POSITIVE LOGITS
    alian
    1.26
    self
    1.10
    atic
    0.99
    unes
    0.85
    chy
    0.84
    displayText
    0.81
    atically
    0.81
    asca
    0.80
    iner
    0.79
    atical
    0.78
    Activations Density 0.202%

    No Known Activations