© 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. 3-RES-JB
    11. 6545
    Prev
    Next
    INDEX
    Explanations

    the word "Mor" followed by a single digit and potentially more characters or numbers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Mor" or related variations in a context, indicating a focus on a specific individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pta
    -0.76
     Tycoon
    -0.74
     Reboot
    -0.69
     sockets
    -0.66
    BOOK
    -0.63
    ãĥ¼ãĥĨãĤ£
    -0.62
     Carbuncle
    -0.62
    ctive
    -0.61
     reasonable
    -0.60
    éĹĺ
    -0.60
    POSITIVE LOGITS
    pheus
    1.20
    rigan
    1.10
    imoto
    1.02
    atorium
    0.94
    rison
    0.86
    als
    0.85
    ison
    0.84
    alf
    0.82
    aband
    0.81
    aff
    0.81
    Activations Density 0.008%

    No Known Activations