© 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. 0-RES-JB
    11. 1203
    Prev
    Next
    INDEX
    Explanations

    words related to the company "Valve" or the concept of valves

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the company Valve and its associated products or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughters
    -0.77
    hom
    -0.76
     Sic
    -0.73
    yss
    -0.72
     prom
    -0.72
    birds
    -0.67
     Kenyan
    -0.66
     birds
    -0.65
     attacked
    -0.65
    hew
    -0.64
    POSITIVE LOGITS
     Valve
    3.93
     valve
    2.65
     valves
    2.12
     Dota
    1.32
     CCP
    1.31
     TI
    1.23
     Gabe
    1.18
     Portal
    1.18
     Volvo
    1.15
    Val
    1.12
    Activations Density 0.019%

    No Known Activations