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

    Neuronpedia

    APICircuit 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. 1395
    Prev
    Next
    INDEX
    Explanations

    commands or instructions to input information

    oai_token-act-pair · gpt-3.5-turbo

    commands or prompts for user input

    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
    killing
    -0.74
     gunned
    -0.67
    killers
    -0.65
     Archangel
    -0.65
    killer
    -0.63
     Singer
    -0.59
     bombed
    -0.59
    MpServer
    -0.59
     Bears
    -0.57
    fml
    -0.57
    POSITIVE LOGITS
    prise
    1.13
    prising
    1.08
    prises
    1.05
    taining
    0.96
    tain
    0.91
    tainment
    0.75
    èª
    0.74
    alde
    0.72
    TAIN
    0.72
    ocent
    0.70
    Activations Density 0.014%

    No Known Activations