© 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. 6-RES-JB
    11. 11545
    Prev
    Next
    INDEX
    Explanations

    phrases related to staying away or being kept out of a place or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating avoidance or exclusion from certain situations or places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elf
    -0.82
    olars
    -0.79
    Ĥİ
    -0.75
    ¾
    -0.74
     testament
    -0.74
    ¨
    -0.71
    imen
    -0.69
    ilib
    -0.68
    ¥
    -0.67
     antioxid
    -0.65
    POSITIVE LOGITS
    agne
    0.71
    ned
    0.69
     altogether
    0.68
    odox
    0.68
     bother
    0.66
    sites
    0.66
    Ïī
    0.65
     Trace
    0.64
    ulnerable
    0.63
     Scy
    0.62
    Activations Density 0.050%

    No Known Activations