© 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. 6-RES-JB
    11. 3661
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a significant level of accomplishment or achievement

    oai_token-act-pair · gpt-3.5-turbo

    references to concepts of effort, achievement, and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ados
    -0.68
    etheless
    -0.65
    atton
    -0.65
    rehens
    -0.63
    Ey
    -0.63
    owers
    -0.62
    gewater
    -0.62
    racuse
    -0.61
    acco
    -0.59
     anth
    -0.58
    POSITIVE LOGITS
    iest
    0.82
     counterparts
    0.78
     selves
    0.66
     intact
    0.66
     credentials
    0.66
     brethren
    0.64
    è»
    0.62
     stake
    0.61
     torch
    0.60
     counterpart
    0.60
    Activations Density 0.215%

    No Known Activations