INDEX

Explanations

high numerical values or counts related to various attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

expandindo

-1.00

PyExc

-0.86

InitVars

-0.82

 WaitForSeconds

-0.82

ValueStyle

-0.79

NameInMap

-0.79

 CanadaChoose

-0.77

SuppressLint

-0.74

 Whiting

-0.71

transQ

-0.70

POSITIVE LOGITS

 Dres

0.70

Dee

0.69

Racer

0.65

 Donuts

0.63

zey

0.62

dem

0.62

Dar

0.62

 Dempsey

0.62

 Racer

0.61

 threats

0.61

Activations Density 0.058%

high numerical values or counts related to various attributes

No Comments

No Known Activations