Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14963
    Prev
    Next
    INDEX
    Explanations

    text related to citations or references

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to citation or referencing sources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quer
    -0.63
     diapers
    -0.61
     untreated
    -0.60
    nesium
    -0.60
     Logged
    -0.60
     NX
    -0.60
    paio
    -0.59
    olen
    -0.57
    ãĥ£
    -0.57
     PID
    -0.56
    POSITIVE LOGITS
    itation
    1.37
    itations
    0.98
    itative
    0.95
    iting
    0.81
    itating
    0.80
    ally
    0.77
    eering
    0.70
    itated
    0.70
     Casting
    0.70
    dating
    0.69
    Activations Density 0.017%

    No Known Activations