INDEX

Explanations

phrases related to the brand "Mazda Lola."

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "ola"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

frames

-0.77

rings

-0.73

liners

-0.73

ergy

-0.72

picking

-0.69

sworth

-0.69

 ancest

-0.65

 unden

-0.65

wcsstore

-0.64

frame

-0.64

POSITIVE LOGITS

uthor

0.95

iffe

0.93

uca

0.91

Ã±o

0.89

ire

0.87

BILITY

0.86

isi

0.85

velength

0.84

zzle

0.84

usk

0.83

Activations Density 0.016%

phrases related to the brand "Mazda Lola."

occurrences of the word "ola"

No Comments

No Known Activations