© 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. 0-RES-JB
    11. 2936
    Prev
    Next
    INDEX
    Explanations

    words related to the action of sampling

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sampling" and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    resses
    -0.75
     Cancel
    -0.74
    odo
    -0.72
    unda
    -0.69
    agra
    -0.68
    eve
    -0.65
    iazep
    -0.64
     compound
    -0.64
    neau
    -0.64
    iano
    -0.63
    POSITIVE LOGITS
     sampling
    3.87
     sampled
    2.07
     sam
    1.40
    sam
    1.38
     rounding
    1.26
    amples
    1.23
     samples
    1.18
     scattering
    1.16
     Sample
    1.08
     filtering
    1.07
    Activations Density 0.031%

    No Known Activations