© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 4480
    Prev
    Next
    INDEX
    Explanations

    terms related to specific technological acronyms followed by corresponding numerical values

    oai_token-act-pair · gpt-3.5-turbo

    references to 'GS' data and its context

    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
    swick
    -0.75
    aneously
    -0.69
    icating
    -0.68
    ted
    -0.67
    landish
    -0.65
    ulatory
    -0.65
    hood
    -0.65
    raged
    -0.64
    fitting
    -0.63
    jad
    -0.63
    POSITIVE LOGITS
    GS
    1.06
    ESSION
    1.04
    earch
    1.03
    IFT
    1.01
    ettings
    1.00
    HT
    0.90
    FFER
    0.87
    OUND
    0.85
    apon
    0.81
    OURCE
    0.80
    Activations Density 0.012%

    No Known Activations