INDEX

Explanations

phrases related to statements or reports and the individuals associated with them

oai_token-act-pair · gpt-3.5-turbo

reported statements or claims made by individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.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

phia

-0.66

aughtered

-0.58

'';

-0.57

Offline

-0.57

 "$:/

-0.55

ggles

-0.54

');

-0.53

ousands

-0.53

 VIDEOS

-0.52

onite

-0.52

POSITIVE LOGITS

 adding

0.89

 referring

0.87

 emphasizing

0.84

 citing

0.80

 sarcast

0.80

 noting

0.78

 implying

0.76

 pointing

0.76

 quoting

0.75

Activations Density 0.140%

phrases related to statements or reports and the individuals associated with them

reported statements or claims made by individuals

No Comments

No Known Activations