© 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. 10109
    Prev
    Next
    INDEX
    Explanations

    phrases related to social, political, or ideological conflict or opposition

    oai_token-act-pair · gpt-3.5-turbo

    references to historical or cultural concepts, especially related to identity and community

    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
     Released
    -0.67
     Bleach
    -0.66
     aval
    -0.66
     Torrent
    -0.63
    released
    -0.63
     Rutherford
    -0.61
     Leilan
    -0.60
    thens
    -0.60
     Reported
    -0.59
    Rot
    -0.58
    POSITIVE LOGITS
     ethos
    1.74
     mantra
    1.51
     motto
    1.50
     tradition
    1.46
     ideals
    1.46
     principles
    1.40
     mentality
    1.36
     philosophy
    1.33
     tenets
    1.33
     creed
    1.33
    Activations Density 0.487%

    No Known Activations