Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 7865
    Prev
    Next
    INDEX
    Explanations

    references to different sensory experiences like warmth, cold, sound, and smell

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of sensory experiences related to weather and ambient conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.78
    Problem
    -0.70
     Founding
    -0.68
     taxpayer
    -0.67
     è£ıè
    -0.66
    Sources
    -0.66
    topic
    -0.66
    ENTION
    -0.66
     unethical
    -0.65
     proble
    -0.65
    POSITIVE LOGITS
     shimmer
    1.18
     throb
    1.07
     breeze
    1.07
     crimson
    1.04
     sparkling
    1.03
     flickering
    1.03
     haze
    1.02
     faintly
    1.01
     soothing
    1.00
     whisper
    1.00
    Activations Density 0.486%

    No Known Activations