© 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. 15839
    Prev
    Next
    INDEX
    Explanations

    references to files or objects that can be connected or added to something else

    oai_token-act-pair · gpt-3.5-turbo

    terms related to attachments and their connections

    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
    Cola
    -0.81
    $$$$
    -0.70
    externalActionCode
    -0.67
    Ô
    -0.65
    ;;;;;;;;;;;;
    -0.63
    Ò
    -0.63
    baum
    -0.62
     Elaine
    -0.61
     rewritten
    -0.61
    solete
    -0.61
    POSITIVE LOGITS
     attachment
    1.05
     attachments
    1.01
    achment
    0.98
     detach
    0.86
     attach
    0.83
    Attach
    0.83
    attach
    0.80
     Pwr
    0.78
    ration
    0.76
    ables
    0.76
    Activations Density 0.018%

    No Known Activations