© 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. 7-RES-JB
    11. 1454
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "foam" with variations in context such as density, material, or application

    oai_token-act-pair · gpt-3.5-turbo

    mentions of foam and its related properties or uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGHTS
    -0.81
    cffffcc
    -0.78
     Noon
    -0.73
    ansk
    -0.69
    hower
    -0.69
     Pis
    -0.68
    OUN
    -0.68
    ONEY
    -0.68
    ocratic
    -0.67
    EGIN
    -0.66
    POSITIVE LOGITS
     coating
    1.45
     insulation
    1.38
     coated
    1.37
     polymer
    1.25
     adhesive
    1.19
     latex
    1.18
     resin
    1.17
     thinner
    1.16
     coat
    1.16
     cloth
    1.15
    Activations Density 0.277%

    No Known Activations