© 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. 10-RES-JB
    11. 16556
    Prev
    Next
    INDEX
    Explanations

    words related to melting, dissolution, or disintegration

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of melting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Assass
    -0.66
    Guard
    -0.62
    ataka
    -0.62
    ours
    -0.61
    CHO
    -0.60
    udence
    -0.58
     Vanguard
    -0.58
    eur
    -0.57
     Belg
    -0.56
    vernment
    -0.56
    POSITIVE LOGITS
    downs
    1.08
     butter
    0.98
     melted
    0.89
     glaciers
    0.85
     melt
    0.83
     ice
    0.82
     melting
    0.81
    down
    0.78
    ember
    0.78
     snow
    0.78
    Activations Density 0.034%

    No Known Activations