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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    6. 22060
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of coming together or consolidating

    oai_token-act-pair · gpt-3.5-turbo

    terms related to cohesion and coherence in ideas or narratives

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

    No Comments

    Negative Logits
     Nikon
    -0.72
    ļéĨĴ
    -0.71
    ĪĴ
    -0.65
    é¾įå¥ij士
    -0.64
    holes
    -0.63
     Delete
    -0.62
     Genie
    -0.62
    Aid
    -0.61
    icals
    -0.61
    +.
    -0.61
    POSITIVE LOGITS
    ortion
    1.07
    urrency
    0.93
    overed
    0.85
    oding
    0.85
    riers
    0.84
    rates
    0.84
    licensed
    0.83
    rum
    0.82
    orders
    0.82
    keyes
    0.81
    Activations Density 0.022%

    No Known Activations