INDEX

Explanations

instances of the word "difficult" to identify challenging concepts or situations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

up

-0.70

as

-0.69

es

-0.69

bra

-0.68

zura

-0.63

-0.61

ber

-0.61

oma

-0.61

POSITIVE LOGITS

BibitemShut

1.16

theless

1.04

 ―――――

1.03

FormTagHelper

1.01

Viki

1.00

 ――――――――

1.00

 nahilalakip

0.98

 iſt

0.98

 myſelf

0.96

határoz

0.94

Activations Density 0.067%

instances of the word "difficult" to identify challenging concepts or situations

No Comments

No Known Activations