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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6-RES-JB
    6. 8061
    Prev
    Next
    INDEX
    Explanations

    terms related to specific institutions or formalities, particularly those related to surveys and regulations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social sciences and general surveys

    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
     cones
    -0.66
     havens
    -0.65
     poles
    -0.59
    Ly
    -0.58
     kittens
    -0.57
    nen
    -0.56
     electrodes
    -0.55
     queen
    -0.55
    NZ
    -0.55
     generations
    -0.54
    POSITIVE LOGITS
    iple
    0.79
    lycer
    0.65
    aviour
    0.64
    oyer
    0.64
    ++)
    0.64
    incial
    0.64
     guiActiveUnfocused
    0.62
    SPONSORED
    0.62
    itutional
    0.61
     Reserved
    0.60
    Activations Density 0.111%

    No Known Activations