© 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. 4-RES-JB
    11. 10157
    Prev
    Next
    INDEX
    Explanations

    phrases related to the company "Citi" and its various activities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "Citi" in various contexts

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

    No Comments

    Negative Logits
    dress
    -0.81
    stroke
    -0.78
    layer
    -0.78
    stairs
    -0.71
     veins
    -0.68
    Temperature
    -0.67
    worthy
    -0.66
    fully
    -0.66
    mil
    -0.64
    bearing
    -0.64
    POSITIVE LOGITS
    Äĩ
    1.25
    atives
    1.15
    iti
    1.04
    ña
    0.96
    ative
    0.94
    emi
    0.92
    zzi
    0.86
    ñ
    0.86
    zed
    0.85
    uting
    0.85
    Activations Density 0.017%

    No Known Activations