INDEX

Explanations

terms related to alternative features or outcomes 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 @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

pexpr

-0.47

intellij

-0.43

enerbahçe

-0.43

ichtung

-0.41

guruan

-0.41

 combinación

-0.41

 Combination

-0.41

 combination

-0.41

ెక్

-0.40

 propOrder

-0.40

POSITIVE LOGITS

 aspects

1.10

 aspetti

0.90

 Aspects

0.88

aspects

0.88

 aspect

0.85

 aspectos

0.84

 facets

0.76

 चीज़ों

0.74

 مشين

0.72

 features

0.72

Activations Density 0.538%

terms related to alternative features or outcomes in various contexts

No Comments

No Known Activations