© 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. 8913
    Prev
    Next
    INDEX
    Explanations

    phrases related to quick actions or acquisitions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to consumption and acquisition

    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
     Danger
    -0.78
    ashtra
    -0.68
     Petraeus
    -0.65
    ukong
    -0.63
    cens
    -0.62
     Tribal
    -0.62
     Support
    -0.62
     srfAttach
    -0.62
    ................................................................
    -0.61
     Tycoon
    -0.61
    POSITIVE LOGITS
    atching
    0.92
    eful
    0.89
     eagerly
    0.87
    Ħ¢
    0.83
    bered
    0.83
    Ĭ
    0.81
    shop
    0.80
     eyed
    0.78
     coveted
    0.78
    atches
    0.77
    Activations Density 0.022%

    No Known Activations