© 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 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. 2-RES-JB
    11. 22702
    Prev
    Next
    INDEX
    Explanations

    technical terms related to hardware components

    oai_token-act-pair · gpt-3.5-turbo

    specifications and features related to products

    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
    qqa
    -0.70
     Samar
    -0.68
    tumblr
    -0.68
    ocument
    -0.66
     Pension
    -0.65
    éĹ
    -0.65
     Finch
    -0.65
    NEY
    -0.60
    ctuary
    -0.59
    invoke
    -0.58
    POSITIVE LOGITS
     aluminum
    0.94
     adjustable
    0.88
     connectors
    0.86
     specifications
    0.86
     radiator
    0.85
     Aluminum
    0.84
     removable
    0.84
     calibration
    0.83
     cooling
    0.83
     adhesive
    0.83
    Activations Density 1.661%

    No Known Activations