© 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. 6-RES-JB
    11. 9643
    Prev
    Next
    INDEX
    Explanations

    words related to technology advancements and comparisons

    oai_token-act-pair · gpt-3.5-turbo

    terms related to comparisons and contrasts between different entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pora
    -0.69
    arios
    -0.63
     flanked
    -0.61
    ariat
    -0.58
    akeru
    -0.58
     preferably
    -0.58
     conspicuous
    -0.57
    istries
    -0.57
    utra
    -0.56
    orum
    -0.55
    POSITIVE LOGITS
    rats
    0.69
    normal
    0.67
     counterparts
    0.67
    ankind
    0.66
    gest
    0.66
    è
    0.61
    ventional
    0.60
    ussia
    0.59
    ahime
    0.58
    ISA
    0.58
    Activations Density 0.420%

    No Known Activations