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. 7-RES-JB
    6. 3301
    Prev
    Next
    INDEX
    Explanations

    specific mentions or discussions that confirm or validate information

    oai_token-act-pair · gpt-3.5-turbo

    instances of confirmation or verification of identities and events

    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
    ĸļ
    -0.87
    BuyableInstoreAndOnline
    -0.73
    jit
    -0.69
    brid
    -0.69
    estyles
    -0.69
    erity
    -0.68
     hoops
    -0.66
    backs
    -0.66
    ener
    -0.65
    perse
    -0.63
    POSITIVE LOGITS
     authenticity
    0.97
     validity
    0.89
     existence
    0.86
    ajor
    0.80
     identities
    0.79
     paternity
    0.78
     occupancy
    0.78
     identity
    0.78
     suspicions
    0.77
     legitimacy
    0.74
    Activations Density 0.118%

    No Known Activations