INDEX

Explanations

connections and relationships involving multiple elements or ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 covered

-0.74

PagerAdapter

-0.64

Rie

-0.63

 знаешь

-0.61

 varit

-0.61

 converted

-0.61

 Pard

-0.61

行了

-0.61

typeorm

-0.60

 trover

-0.60

POSITIVE LOGITS

 help

0.84

 putea

0.80

 بيها

0.78

 make

0.78

 build

0.76

 create

0.74

 Pennington

0.74

 take

0.74

to

0.71

 intervene

0.70

Activations Density 0.394%

connections and relationships involving multiple elements or ideas

No Comments

No Known Activations