© 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. 7-RES-JB
    11. 1744
    Prev
    Next
    INDEX
    Explanations

    phrases related to constraints or limitations

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "const" and its variations, indicating a focus on issues related to conservation or constraint

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cules
    -0.79
    dos
    -0.76
    pmwiki
    -0.74
    WARE
    -0.70
    sonian
    -0.69
    ctors
    -0.68
    grab
    -0.67
    bones
    -0.65
     nerv
    -0.64
    ombies
    -0.64
    POSITIVE LOGITS
    ellation
    1.37
    ipation
    1.28
    abulary
    1.23
    expr
    1.21
    itution
    1.10
    ricting
    1.08
    rast
    1.07
    rict
    1.06
    ricted
    1.06
    antly
    1.03
    Activations Density 0.019%

    No Known Activations