INDEX

Explanations

expressions of gratitude

oai_token-act-pair · gpt-3.5-turbo

expressions of gratitude

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

viol

-0.63

)]

-0.59

 claimed

-0.59

 displ

-0.59

conserv

-0.59

surv

-0.58

chart

-0.58

iche

-0.58

imeter

-0.56

 territory

-0.56

POSITIVE LOGITS

sir

0.95

 Thank

0.81

giving

0.81

 kindly

0.79

 thank

0.78

 THANK

0.77

ratulations

0.76

rats

0.74

 guys

0.73

 sincerely

0.71

Activations Density 0.050%

expressions of gratitude

expressions of gratitude

No Comments

No Known Activations