© 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. 2-RES-JB
    11. 6578
    Prev
    Next
    INDEX
    Explanations

    words related to premeditated actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to medical contexts and conditions

    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
    chnology
    -0.77
     fundament
    -0.70
    issues
    -0.66
     Objective
    -0.65
    BOOK
    -0.65
    interface
    -0.63
    ··
    -0.60
    framework
    -0.60
    ZI
    -0.58
    RFC
    -0.58
    POSITIVE LOGITS
    ieval
    1.25
    ication
    1.08
    ications
    1.05
    icated
    1.03
    iterranean
    1.01
    icate
    1.00
    icative
    0.91
    rill
    0.91
    med
    0.91
    igree
    0.87
    Activations Density 0.010%

    No Known Activations