© 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. 12302
    Prev
    Next
    INDEX
    Explanations

    phrases related to enterprise and business applications

    oai_token-act-pair · gpt-3.5-turbo

    references to enterprise-level concepts and applications

    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
    zbollah
    -0.71
    adder
    -0.66
    attering
    -0.66
    kowski
    -0.65
    idi
    -0.65
     Drawing
    -0.64
    dim
    -0.61
    ipp
    -0.61
    bid
    -0.61
    emb
    -0.60
    POSITIVE LOGITS
     enterprise
    1.02
     enterprises
    0.90
    prise
    0.89
    eers
    0.87
     ventures
    0.85
    tainment
    0.82
    olicy
    0.78
     venture
    0.77
     endeavor
    0.76
    ively
    0.76
    Activations Density 0.004%

    No Known Activations