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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 4263
    Prev
    Next
    INDEX
    Explanations

    instances where something has already been done or is in place

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of something being "already" established or existing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    case
    -0.84
    istics
    -0.79
    udge
    -0.79
    rary
    -0.75
    rent
    -0.71
    ueller
    -0.69
    rus
    -0.68
    orie
    -0.67
    rarily
    -0.67
    onnaissance
    -0.66
    POSITIVE LOGITS
     underway
    0.89
     existed
    0.84
     exists
    0.84
     surpassed
    0.81
     begun
    0.76
     knew
    0.76
     fulfilled
    0.76
     booked
    0.73
     served
    0.73
     racked
    0.73
    Activations Density 0.032%

    No Known Activations