© 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. 0-RES-JB
    11. 16473
    Prev
    Next
    INDEX
    Explanations

    mentions or references to allegations or accusations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    scape
    -0.71
    rain
    -0.68
    hn
    -0.67
    ool
    -0.65
    owa
    -0.64
    Prep
    -0.61
     Optim
    -0.61
     alike
    -0.60
    arity
    -0.60
    alone
    -0.59
    POSITIVE LOGITS
     alleged
    3.55
     purported
    2.17
     allegedly
    2.07
     accused
    1.89
     alleges
    1.88
     allege
    1.85
     allegation
    1.82
     suspected
    1.79
     allegations
    1.74
     purportedly
    1.61
    Activations Density 0.015%

    No Known Activations