INDEX

Explanations

phrases related to accusations or claims of wrongdoing

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.94

띄

-0.67

/***

-0.63

//<

-0.58

displayquote

-0.58

HasKey

-0.58

tw

-0.58

//{

-0.57

win

-0.57

POSITIVE LOGITS

Juf

1.76

 Khart

1.67

 Minang

1.66

 thut

1.60

fta

1.50

 bandung

1.50

 jaya

1.48

 accla

1.48

aen

1.48

 increa

1.46

Activations Density 0.045%

phrases related to accusations or claims of wrongdoing

No Comments

No Known Activations