© 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. 11-RES-JB
    11. 16503
    Prev
    Next
    INDEX
    Explanations

    words related to medical treatments or procedures

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific syllable or sound pattern in words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sins
    -0.69
     Straw
    -0.64
     contrasting
    -0.63
     silence
    -0.60
     Hitman
    -0.57
     Estimated
    -0.56
     Gulf
    -0.55
    taboola
    -0.54
     ss
    -0.54
     kindred
    -0.53
    POSITIVE LOGITS
    ierrez
    1.44
    rition
    1.34
    iful
    1.25
    tle
    1.24
    ifully
    1.24
    cheon
    1.22
    ainment
    1.11
    opian
    1.11
    rient
    1.09
    ritional
    1.08
    Activations Density 0.052%

    No Known Activations