INDEX

Explanations

elements of communication related to requests and instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

MigrationBuilder

-0.69

RegistryLite

-0.62

 propOrder

-0.59

URLException

-0.57

Ӕ

-0.55

HasForeignKey

-0.54

 Pyrenees

-0.54

ModelAdmin

-0.54

nocache

-0.53

 dagegen

-0.53

POSITIVE LOGITS

 Stay

1.08

 stay

1.04

Stay

0.98

stay

0.83

 stayed

0.82

 STAY

0.78

Don

0.77

 stays

0.76

 Check

0.75

 head

0.74

Activations Density 0.138%

elements of communication related to requests and instructions

No Comments

No Known Activations