© 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. 7-RES-JB
    11. 13464
    Prev
    Next
    INDEX
    Explanations

    terms related to physical fitness or health

    oai_token-act-pair · gpt-3.5-turbo

    repetitive phrases or patterns in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obook
    -0.69
    Introduced
    -0.67
    Advertisement
    -0.63
    abo
    -0.63
    ,[
    -0.62
    ajor
    -0.62
    bryce
    -0.62
    agram
    -0.60
     âĢķ
    -0.60
    Adult
    -0.59
    POSITIVE LOGITS
     huh
    1.42
     eh
    1.21
     please
    0.98
     Pt
    0.86
     sir
    0.76
     yes
    0.76
     yeah
    0.74
     etc
    0.71
     beware
    0.68
     meanwhile
    0.68
    Activations Density 0.341%

    No Known Activations