© 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. 975
    Prev
    Next
    INDEX
    Explanations

    the word "bet."

    oai_token-act-pair · gpt-4-turbo

    instances where the word "bet" is used

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making predictions or assumptions

    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
    ĸļ
    -0.83
     Flavoring
    -0.74
    ISTER
    -0.70
    anwhile
    -0.70
    ocumented
    -0.69
     Blaze
    -0.69
    VILLE
    -0.66
     Symptoms
    -0.65
    pmwiki
    -0.65
    issance
    -0.63
    POSITIVE LOGITS
     bet
    1.07
     bets
    1.07
    hesda
    1.05
    terson
    0.97
    ting
    0.91
    ters
    0.89
     peg
    0.81
    bet
    0.80
    rop
    0.79
    tery
    0.76
    Activations Density 0.008%

    No Known Activations