© 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. 3129
    Prev
    Next
    INDEX
    Explanations

    phrases related to playing a significant or important role in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a significant role or contribution 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
     dumps
    -0.70
     vomit
    -0.70
     batches
    -0.68
    igslist
    -0.68
    aturdays
    -0.67
     hugs
    -0.67
     Walls
    -0.67
     Colleges
    -0.67
     tattoos
    -0.66
     lashes
    -0.64
    POSITIVE LOGITS
     role
    1.23
    role
    1.23
    Role
    0.87
     pivotal
    0.87
     Role
    0.83
     roles
    0.80
     disadvantage
    0.77
    lot
    0.76
     decisive
    0.75
     disproportionate
    0.75
    Activations Density 0.062%

    No Known Activations