© 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
    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. 7748
    Prev
    Next
    INDEX
    Explanations

    samples or testing related terms within a context

    oai_token-act-pair · gpt-3.5-turbo

    references to sample sizes in research contexts

    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
    iour
    -0.73
    eve
    -0.69
    bol
    -0.66
    Fighting
    -0.65
    mounted
    -0.64
    Wars
    -0.62
     undone
    -0.61
    rir
    -0.61
    Fight
    -0.61
    acia
    -0.61
    POSITIVE LOGITS
     sample
    3.86
     samples
    2.86
     Sample
    2.84
    sample
    2.60
    Sample
    2.45
     sampling
    2.37
     sampled
    2.08
    amples
    1.48
     specimen
    1.44
     dataset
    1.42
    Activations Density 0.015%

    No Known Activations