© 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. 4-RES-JB
    11. 7328
    Prev
    Next
    INDEX
    Explanations

    phrases related to project planning or implementation stages

    oai_token-act-pair · gpt-3.5-turbo

    mentions of different phases in processes or projects

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

    No Comments

    Negative Logits
    ILLE
    -1.05
    riad
    -0.87
     Cosponsors
    -0.81
    HCR
    -0.77
     glim
    -0.77
    inately
    -0.76
    esome
    -0.75
     sqor
    -0.72
    llah
    -0.71
    intent
    -0.71
    POSITIVE LOGITS
     Phase
    0.97
     phase
    0.97
     phases
    0.88
     stages
    0.79
    phase
    0.76
    hift
    0.74
     stage
    0.71
    arthed
    0.69
    tenance
    0.69
    lees
    0.69
    Activations Density 0.011%

    No Known Activations