INDEX

Explanations

references to interventions in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

TypedDataSet

-0.65

blaze

-0.64

 Causeway

-0.62

Rams

-0.62

Демографія

-0.60

arrange

-0.60

 kaynağından

-0.57

">−

-0.56

hauser

-0.56

اخت

-0.56

POSITIVE LOGITS

 interventions

0.75

 Convert

0.74

 Newer

0.74

 Interventions

0.72

Intervention

0.71

Convert

0.68

 Intervention

0.65

 newer

0.64

 intervention

0.64

 cubana

0.64

Activations Density 0.066%

references to interventions in various contexts

No Comments

No Known Activations