© 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. 7-RES-JB
    11. 11624
    Prev
    Next
    INDEX
    Explanations

    phrases related to different levels or branches within systems or organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to levels or branches of organization and society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odore
    -0.75
    ndra
    -0.73
    ogram
    -0.72
    ograms
    -0.70
     Picks
    -0.70
    pher
    -0.68
    days
    -0.66
    dayName
    -0.64
    oning
    -0.64
    kson
    -0.64
    POSITIVE LOGITS
     society
    0.80
     socioeconomic
    0.75
     life
    0.74
     taxp
    0.74
     deprivation
    0.72
     consciousness
    0.70
    edIn
    0.69
     income
    0.69
     human
    0.69
     endeavor
    0.67
    Activations Density 0.149%

    No Known Activations