© 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. 12190
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration and revelation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "discover" in various contexts

    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
    annis
    -0.75
    hovah
    -0.75
    yip
    -0.70
    cius
    -0.69
    paying
    -0.68
    EStreamFrame
    -0.68
    ortunately
    -0.68
     aver
    -0.68
     paced
    -0.67
    perty
    -0.67
    POSITIVE LOGITS
    ibility
    0.96
    ãĤ¦ãĤ¹
    0.91
    çīĪ
    0.89
    iveness
    0.88
    Discover
    0.85
    Ô
    0.84
    使
    0.84
    ibles
    0.83
     Wond
    0.82
    æ©
    0.81
    Activations Density 0.011%

    No Known Activations