INDEX

Explanations

specific phrases or claims related to discussions and debates about societal and political issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 actionGroup

-0.75

itaire

-0.72

icter

-0.71

*/

-0.70

 Afgh

-0.70

 warr

-0.69

FTWARE

-0.69

MpServer

-0.68

*/

-0.67

ixture

-0.65

POSITIVE LOGITS

 quotes

1.02

 reply

0.99

yrics

0.95

 replies

0.94

 replied

0.94

 echoed

0.93

 referring

0.92

 quotation

0.90

 quote

0.90

 echoes

0.87

Activations Density 0.259%

specific phrases or claims related to discussions and debates about societal and political issues

No Comments

No Known Activations