© 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. 8-RES-JB
    11. 22420
    Prev
    Next
    INDEX
    Explanations

    personal statements or opinions

    oai_token-act-pair · gpt-3.5-turbo

    the word "My" and variations of personal pronouns or possessive adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    س
    -0.75
    qq
    -0.74
    Ïī
    -0.74
    ãĥ´ãĤ¡
    -0.73
    POST
    -0.72
    adobe
    -0.71
    ����
    -0.70
    ensis
    -0.70
    âľ
    -0.69
    192
    -0.69
    POSITIVE LOGITS
     goal
    1.29
     aim
    1.18
     biggest
    1.16
     motto
    1.10
    anmar
    1.10
    stery
    1.09
     favourite
    1.09
     inability
    1.08
     apologies
    1.08
     idea
    1.07
    Activations Density 0.133%

    No Known Activations