© 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. 18710
    Prev
    Next
    INDEX
    Explanations

    specific text embellishments or formatting patterns, such as special characters or text in single quotes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "doesn't" in various contexts

    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
     disadvant
    -0.58
     mathemat
    -0.58
     CLR
    -0.57
     misunder
    -0.57
     Negro
    -0.56
     Palestin
    -0.55
     constitu
    -0.55
     Chero
    -0.53
     contrace
    -0.53
    ozy
    -0.53
    POSITIVE LOGITS
    ï¸ı
    1.19
    Balt
    0.79
    ï¸
    0.78
    eric
    0.74
    âĻ
    0.72
    forward
    0.71
    tre
    0.70
    ç
    0.70
    rh
    0.68
    SHIP
    0.68
    Activations Density 0.343%

    No Known Activations