INDEX

Explanations

names and terms associated with individuals and their actions, particularly in a context that involves criticism or accountability

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

<bos>

-1.33

PerformLayout

-0.70

anganronpa

-0.66

Ethylbenzene

-0.61

Datuak

-0.57

 PeEnEo

-0.51

bean

-0.50

ModelBuilder

-0.50

벳

-0.49

عرض

-0.49

POSITIVE LOGITS

 maksi

1.16

 saar

1.00

 alha

0.95

duk

0.93

 maroc

0.93

 lele

0.92

 osal

0.91

 kram

0.90

 marseille

0.89

 naer

0.88

Activations Density 0.265%

names and terms associated with individuals and their actions, particularly in a context that involves criticism or accountability

No Known Activations