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. 3-RES-JB
    6. 7910
    Prev
    Next
    INDEX
    Explanations

    words related to physical sensations or qualities, particularly those related to physical or emotional intensity

    oai_token-act-pair · gpt-3.5-turbo

    various forms of academic or technical terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cheong
    -0.75
    places
    -0.66
    velt
    -0.66
    Adds
    -0.63
     shuffle
    -0.63
     Gret
    -0.61
     NXT
    -0.60
     answer
    -0.59
     shine
    -0.58
     mobs
    -0.57
    POSITIVE LOGITS
    ophen
    0.83
    Sensor
    0.82
    ãĤ¼ãĤ¦ãĤ¹
    0.82
    tions
    0.81
    Weather
    0.78
    EMENT
    0.77
    uration
    0.77
    ccording
    0.75
    pillar
    0.75
    ÃĽ
    0.74
    Activations Density 0.211%

    No Known Activations