© 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. 2-RES-JB
    11. 17247
    Prev
    Next
    INDEX
    Explanations

    references to legal procedures relating to appeals

    oai_token-act-pair · gpt-3.5-turbo

    references to "Internet" or related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.85
    artifacts
    -0.84
     Gleaming
    -0.82
    wordpress
    -0.81
    */(
    -0.80
    mith
    -0.79
    éĹĺ
    -0.76
    ¶ħ
    -0.75
    姫
    -0.74
    lling
    -0.74
    POSITIVE LOGITS
    ellect
    1.26
    ention
    1.17
    ensity
    1.11
    ellig
    1.04
    uitive
    1.02
    estinal
    1.00
    ensive
    1.00
    elligence
    0.97
    ENTION
    0.95
    elligent
    0.90
    Activations Density 0.010%

    No Known Activations