INDEX

Explanations

the word "familiar" or variations of it within the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "familiar."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

mpeg

-0.76

inth

-0.68

pi

-0.68

scoring

-0.68

reme

-0.68

chance

-0.67

Chance

-0.66

rah

-0.66

rate

-0.65

oner

-0.64

POSITIVE LOGITS

 familiar

1.23

 unfamiliar

0.94

iliar

0.94

isable

0.93

amiliar

0.91

 familiarity

0.85

 recognizable

0.84

 faces

0.82

ciating

0.82

idad

0.81

Activations Density 0.016%

the word "familiar" or variations of it within the text

instances of the word "familiar."

No Comments

No Known Activations