INDEX

Explanations

occurrences of the word "so"

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "to do so" or variations thereof

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Flavoring

-0.63

Lau

-0.63

pread

-0.61

 Places

-0.61

Ĩ

-0.61

 Neighborhood

-0.60

 Moving

-0.60

 Dreams

-0.59

 Children

-0.59

 Kang

-0.59

POSITIVE LOGITS

oner

1.08

zin

0.91

 anonymously

0.87

oths

0.81

othe

0.79

iety

0.78

----------------------------------------------------------------

0.78

.–

0.77

.</

0.75

 abundantly

0.75

Activations Density 0.027%

occurrences of the word "so"

instances of the phrase "to do so" or variations thereof

No Comments

No Known Activations