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. 14674
    Prev
    Next
    INDEX
    Explanations

    phrases related to customer service or clients

    oai_token-act-pair · gpt-3.5-turbo

    references to patrons or the concept of patronage

    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
    MO
    -0.77
    ATHER
    -0.74
    AR
    -0.73
    RAY
    -0.71
    ARR
    -0.71
     Recon
    -0.70
    cross
    -0.67
    RAM
    -0.65
    NOR
    -0.65
    grass
    -0.64
    POSITIVE LOGITS
     patrons
    1.60
    ĸļ
    1.04
     patron
    0.92
    umers
    0.90
    ateurs
    0.90
     patronage
    0.88
     drinkers
    0.85
     eleph
    0.82
    hip
    0.81
    isine
    0.80
    Activations Density 0.010%

    No Known Activations