© 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 EvalsExportsinterp-engineNEWAPI 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. 8-RES-JB
    11. 24240
    Prev
    Next
    INDEX
    Explanations

    adjectives related to temperature

    oai_token-act-pair · gpt-3.5-turbo

    adjectives and phrases describing conditions or scales in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocate
    -0.74
    ¶ħ
    -0.69
    ibraries
    -0.68
    upon
    -0.68
    anooga
    -0.68
    ierre
    -0.65
    lance
    -0.65
    ritis
    -0.65
    auga
    -0.64
    ventus
    -0.63
    POSITIVE LOGITS
     occasions
    1.46
     basis
    1.44
     occasion
    1.31
     behalf
    1.27
     grounds
    1.12
     doorstep
    1.12
     campuses
    1.02
     pretext
    1.02
     footing
    1.02
     sidelines
    0.98
    Activations Density 0.477%

    No Known Activations