© 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. 2-RES-JB
    11. 9374
    Prev
    Next
    INDEX
    Explanations

    phrases related to political power or authority

    oai_token-act-pair · gpt-3.5-turbo

    references to authority or influence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eor
    -0.66
     Alvarez
    -0.66
    Sil
    -0.65
     Absent
    -0.64
    Gil
    -0.64
    rian
    -0.63
     Murd
    -0.62
    ded
    -0.61
     Tud
    -0.61
     Ign
    -0.61
    POSITIVE LOGITS
     powers
    1.02
    Reviewer
    0.92
    hell
    0.90
    uits
    0.84
     delegated
    0.82
     superpower
    0.81
     conferred
    0.79
    oshenko
    0.75
    wu
    0.72
    olve
    0.72
    Activations Density 0.013%

    No Known Activations