© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 17786
    Prev
    Next
    INDEX
    Explanations

    terms related to technical specifications, such as blueprints, schematics, and playbooks

    oai_token-act-pair · gpt-3.5-turbo

    terms related to planning and strategic frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aho
    -0.81
    adow
    -0.81
    adows
    -0.73
    awar
    -0.71
    ities
    -0.70
    evil
    -0.68
    anger
    -0.68
    otine
    -0.67
    croft
    -0.66
    ads
    -0.66
    POSITIVE LOGITS
     blueprint
    1.32
     Blueprint
    1.22
    eers
    0.87
     checklist
    0.86
    urally
    0.86
     playbook
    0.85
    \\\\\\\\
    0.84
     schematic
    0.83
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    0.81
     outline
    0.79
    Activations Density 0.008%

    No Known Activations