© 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. 8-RES-JB
    11. 6179
    Prev
    Next
    INDEX
    Explanations

    phrases about progress or advancement over a significant period of time

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe a prolonged duration or significant progress over time

    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
     Thumbnails
    -0.72
    Mods
    -0.67
    iances
    -0.67
    illions
    -0.66
    rencies
    -0.65
    leck
    -0.64
     Territories
    -0.64
    Always
    -0.63
    oppers
    -0.63
    selves
    -0.63
    POSITIVE LOGITS
    itudinal
    1.13
    sword
    1.12
    itud
    1.10
     overdue
    1.05
    shore
    1.01
     awaited
    0.96
     ago
    0.96
     term
    0.94
    itude
    0.88
     lasting
    0.87
    Activations Density 0.043%

    No Known Activations