© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4-RES-JB
    11. 7004
    Prev
    Next
    INDEX
    Explanations

    words related to dogs trained for specific purposes

    oai_token-act-pair · gpt-3.5-turbo

    the mention of specific dog breeds, particularly the K-9 breed in various contexts

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

    No Comments

    Negative Logits
    ãģ®éŃĶ
    -0.84
     guiActiveUn
    -0.68
     cir
    -0.65
     bere
    -0.64
    OPLE
    -0.63
     "$:/
    -0.63
    auga
    -0.62
    çĶ°
    -0.62
    inois
    -0.62
    uez
    -0.61
    POSITIVE LOGITS
    shaped
    1.05
    sized
    1.03
    dimensional
    1.02
    government
    1.02
    level
    1.01
    style
    0.97
    type
    0.94
    tier
    0.93
    series
    0.91
    specific
    0.89
    Activations Density 0.097%

    No Known Activations