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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16078
    Prev
    Next
    INDEX
    Explanations

    terms related to operating systems (OS)

    oai_token-act-pair · gpt-3.5-turbo

    references to specific scientific journals or publications

    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
    aneous
    -0.82
     msec
    -0.79
     Citation
    -0.72
    ered
    -0.71
    TextColor
    -0.70
    starter
    -0.68
     Reserved
    -0.67
    table
    -0.67
     Hots
    -0.64
    ministic
    -0.63
    POSITIVE LOGITS
     ANGEL
    1.12
    CAR
    0.96
    HA
    0.95
    omal
    0.90
    leep
    0.90
    pace
    0.88
    ECTION
    0.88
    clerosis
    0.87
    CI
    0.87
    uba
    0.87
    Activations Density 0.009%

    No Known Activations