© 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. 9-RES-JB
    11. 15507
    Prev
    Next
    INDEX
    Explanations

    phrases indicating things that are in progress or being planned

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to projects or developments in progress

    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
    gencies
    -0.65
     cared
    -0.63
    dad
    -0.62
    1978
    -0.62
     screamed
    -0.60
    CVE
    -0.60
    ãĥĺ
    -0.60
    Viol
    -0.59
     proclaimed
    -0.58
    gio
    -0.57
    POSITIVE LOGITS
     plans
    0.85
     phases
    0.81
     feasibility
    0.77
     phase
    0.75
     Phase
    0.74
    abouts
    0.74
    rils
    0.74
     stages
    0.69
     developments
    0.67
     revisions
    0.67
    Activations Density 0.402%

    No Known Activations