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. 8-RES-JB
    6. 23032
    Prev
    Next
    INDEX
    Explanations

    phrases related to urging, asking for personal or financial support, and expressing gratitude

    oai_token-act-pair · gpt-3.5-turbo

    mentions of locations and communities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filler
    -0.65
    uristic
    -0.61
     Heist
    -0.60
     vacuum
    -0.59
     rehearsal
    -0.59
     scrimmage
    -0.58
    Reloaded
    -0.57
    obar
    -0.55
     elim
    -0.55
    atile
    -0.54
    POSITIVE LOGITS
     alike
    1.19
    who
    0.95
     who
    0.92
     whom
    0.91
     hereafter
    0.83
     wishing
    0.80
     thereof
    0.79
    whose
    0.78
     thereto
    0.74
     whose
    0.71
    Activations Density 0.736%

    No Known Activations