© 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. 9262
    Prev
    Next
    INDEX
    Explanations

    the word "third" preceded by another word

    oai_token-act-pair · gpt-3.5-turbo

    references to third-party involvement or entities

    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
    ISTORY
    -0.70
     Guides
    -0.67
    Money
    -0.65
    NUM
    -0.65
    Boost
    -0.64
    å¸
    -0.63
     pastoral
    -0.63
    åħ
    -0.63
     Limits
    -0.63
    Attributes
    -0.62
    POSITIVE LOGITS
     baseman
    1.18
    rd
    1.13
    ority
    0.87
    irty
    0.87
    uous
    0.83
    ieth
    0.83
    quel
    0.82
    orne
    0.81
     inning
    0.79
    emate
    0.79
    Activations Density 0.024%

    No Known Activations