© 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. 0-RES-JB
    11. 12428
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals attempting to recover or regain something

    oai_token-act-pair · gpt-3.5-turbo

    references to specific people or characters, particularly in connection with groups or collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Gary
    -0.76
     Logged
    -0.71
     experien
    -0.71
    Reviewer
    -0.69
     Berm
    -0.67
     Collider
    -0.67
     Mutant
    -0.66
     Starship
    -0.66
     milestones
    -0.64
    otor
    -0.64
    POSITIVE LOGITS
    oup
    3.26
    OUP
    1.59
     Joyce
    1.59
     Coup
    1.27
    inx
    1.20
    iven
    1.10
    ox
    1.06
     Vi
    1.02
     Que
    1.01
     Naj
    1.00
    Activations Density 0.035%

    No Known Activations