© 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. 18480
    Prev
    Next
    INDEX
    Explanations

    cryptic words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    words related to various types of food or eating

    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
     Zan
    -0.64
     Integrity
    -0.64
     Brill
    -0.61
     Kinnikuman
    -0.59
     aspirin
    -0.59
     deceptive
    -0.57
     initials
    -0.57
     illegitimate
    -0.57
     Barber
    -0.57
     Lazarus
    -0.56
    POSITIVE LOGITS
    ooth
    1.00
    ove
    0.93
    oop
    0.92
    uff
    0.91
    ypes
    0.90
    icz
    0.89
    ool
    0.88
    atch
    0.88
    ood
    0.88
    ont
    0.87
    Activations Density 0.405%

    No Known Activations