© 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. 24040
    Prev
    Next
    INDEX
    Explanations

    timestamps in the format of "PM" or "AM"

    oai_token-act-pair · gpt-3.5-turbo

    time indicators related to PM and AM

    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
    leans
    -0.87
    kefeller
    -0.78
     Schwar
    -0.72
    wikipedia
    -0.71
    ãĤ½
    -0.70
    ãĥ¼ãĤ¯
    -0.69
    ttes
    -0.69
    come
    -0.68
    heid
    -0.67
    tyard
    -0.67
    POSITIVE LOGITS
    PM
    1.05
     PM
    1.04
    essage
    0.95
    PD
    0.86
     EDT
    0.85
     EST
    0.82
     IST
    0.80
     pm
    0.80
     PST
    0.75
     CST
    0.75
    Activations Density 0.009%

    No Known Activations