INDEX

Explanations

words related to notable individuals and specific events, potentially from news articles or online forums

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Configuration

jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

HuggingFaceFW/fineweb

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-0.99

 ***!

-0.74

__;

-0.73

RectangleBorder

-0.72

HtmlAttribute

-0.70

-0.69

 >=",

-0.69

<",

-0.67

;#

-0.65

-0.64

POSITIVE LOGITS

 impra

2.16

 increa

2.12

 disagre

2.07

 maneu

2.03

 affor

2.00

 emphat

1.98

 reluct

1.94

 unspeak

1.93

 unden

1.93

fuf

1.93

Activations Density 4.557%

words related to notable individuals and specific events, potentially from news articles or online forums

No Comments

No Known Activations