© 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. 10-RES-JB
    11. 17369
    Prev
    Next
    INDEX
    Explanations

    different forms of the verb "to do" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    discussions around activities and media consumption options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attribution
    -0.76
    èĢħ
    -0.75
    rium
    -0.75
    iversal
    -0.74
     Parameters
    -0.74
     opacity
    -0.71
    onom
    -0.70
     definitive
    -0.70
    sylv
    -0.70
     supremacy
    -0.69
    POSITIVE LOGITS
     drank
    1.32
     eat
    1.29
     drink
    1.23
     ate
    1.16
     swim
    1.12
     partake
    1.10
     cook
    1.07
    ercise
    1.06
     stroll
    1.05
     recite
    1.05
    Activations Density 0.355%

    No Known Activations