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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 16933
    Prev
    Next
    INDEX
    Explanations

    numerical values containing the number 5 and 9

    oai_token-act-pair · gpt-3.5-turbo

    the number five, particularly in numerical contexts

    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
     Hort
    -0.71
    é¾įå¥ij士
    -0.68
    unity
    -0.67
    udeb
    -0.66
    recogn
    -0.65
     Assange
    -0.64
    iasis
    -0.63
    ãģ®å®
    -0.60
    ocard
    -0.60
    ovic
    -0.59
    POSITIVE LOGITS
    Thirty
    0.91
    010
    0.83
    th
    0.82
    âĺħ
    0.81
    anging
    0.80
    43
    0.79
    â̳
    0.79
    42
    0.77
    67
    0.76
    OWER
    0.75
    Activations Density 0.089%

    No Known Activations