© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 11612
    Prev
    Next
    INDEX
    Explanations

    information related to survey margins of error

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistical margins of error and polling results

    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
    SpaceEngineers
    -0.75
    module
    -0.73
    dos
    -0.71
    modules
    -0.71
    Merit
    -0.69
    mast
    -0.65
    mods
    -0.65
    proc
    -0.65
    dies
    -0.65
    mobi
    -0.64
    POSITIVE LOGITS
     +/-
    0.89
     margin
    0.86
     weighted
    0.81
     sampling
    0.76
     interval
    0.73
    renheit
    0.73
     error
    0.73
     uncertainties
    0.71
     undecided
    0.71
    negie
    0.71
    Activations Density 0.093%

    No Known Activations