© 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. 18725
    Prev
    Next
    INDEX
    Explanations

    accelerated or intense actions or experiences

    oai_token-act-pair · gpt-3.5-turbo

    terms related to fast-paced action and gameplay mechanics

    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
     Marketable
    -0.79
    leaf
    -0.73
    åħī
    -0.73
    soType
    -0.72
    redit
    -0.72
    lease
    -0.71
    Statement
    -0.68
    cci
    -0.67
    chin
    -0.67
    ploy
    -0.67
    POSITIVE LOGITS
     gameplay
    1.20
     adventure
    1.17
     thriller
    1.15
     realism
    1.15
     genre
    1.11
     RPG
    1.00
     sandbox
    0.99
     rog
    0.99
     mayhem
    0.99
     RPGs
    0.99
    Activations Density 0.195%

    No Known Activations