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. 6843
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical project management and development processes

    oai_token-act-pair · gpt-3.5-turbo

    references to teams, development processes, and production quality in various contexts

    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
    beck
    -0.81
    olson
    -0.76
    aucas
    -0.70
     mosqu
    -0.69
    urnal
    -0.69
    awaru
    -0.68
    agher
    -0.67
    vous
    -0.65
    odka
    -0.65
    clinton
    -0.65
    POSITIVE LOGITS
     Engineers
    0.85
     UE
    0.79
     Gleaming
    0.75
    flows
    0.74
    Factory
    0.73
     Architecture
    0.70
     guiActiveUnfocused
    0.70
     Concepts
    0.69
     specification
    0.67
     Parables
    0.67
    Activations Density 0.642%

    No Known Activations