INDEX

Explanations

statements or quotes starting with the word "that"

oai_token-act-pair · gpt-3.5-turbo

the word "that" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

Tank

-0.72

arest

-0.70

ress

-0.63

Pocket

-0.63

Pont

-0.63

lete

-0.62

Ü

-0.61

STE

-0.61

Î±

-0.60

plus

-0.60

POSITIVE LOGITS

 although

1.15

"[

1.05

 while

0.81

 "...

0.79

 despite

0.77

 whilst

0.77

 "âĢ¦

0.76

 whereas

0.75

soever

0.74

'[

0.73

Activations Density 0.226%

statements or quotes starting with the word "that"

the word "that" in various contexts

No Comments

No Known Activations