© 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. 1-RES-JB
    11. 23555
    Prev
    Next
    INDEX
    Explanations

    phrases related to making or canceling reservations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of reservations or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    drm
    -0.71
    chie
    -0.70
    ramid
    -0.68
    aeus
    -0.68
    win
    -0.68
    tra
    -0.67
    obs
    -0.66
    squ
    -0.66
    Win
    -0.64
    ©¶æ
    -0.64
    POSITIVE LOGITS
     reservation
    1.43
     reservations
    1.37
     Reserv
    0.93
    ervation
    0.80
     tickets
    0.77
    aste
    0.76
     booking
    0.76
     Restaur
    0.75
    erv
    0.75
     Valiant
    0.74
    Activations Density 0.010%

    No Known Activations