Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 24065
    Prev
    Next
    INDEX
    Explanations

    specific time zone abbreviations such as 'PDT' and 'PST'

    oai_token-act-pair · gpt-3.5-turbo

    time zone abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amac
    -0.75
    hist
    -0.70
    venge
    -0.70
    actor
    -0.69
    proof
    -0.66
    gotten
    -0.65
    neys
    -0.64
    stay
    -0.64
     welfare
    -0.64
    pir
    -0.63
    POSITIVE LOGITS
     EDT
    1.05
     CET
    0.94
    DAQ
    0.89
     PDT
    0.86
     EST
    0.79
    EMBER
    0.79
     CST
    0.77
     GMT
    0.76
     KO
    0.75
     +/-
    0.74
    Activations Density 0.022%

    No Known Activations