© 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. 2-RES-JB
    6. 1526
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or contrasts

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating progress, change, or evolution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Machines
    -0.39
     Bund
    -0.39
     Sing
    -0.39
     Surve
    -0.38
    planes
    -0.37
    cel
    -0.36
    opers
    -0.36
     bats
    -0.36
    apes
    -0.36
    bats
    -0.35
    POSITIVE LOGITS
     understatement
    0.51
    allery
    0.47
    emonium
    0.47
    ierre
    0.43
     indication
    0.42
    ãĥķãĤ©
    0.40
     distingu
    0.39
     partName
    0.39
     precedent
    0.38
     affiliate
    0.37
    Activations Density 2.677%

    No Known Activations