INDEX

Explanations

words related to geographical locations or specific names

oai_token-act-pair · gpt-3.5-turbo

special characters or symbols

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

strip

-0.75

stri

-0.75

versions

-0.74

istics

-0.73

ription

-0.68

 thesis

-0.68

wagen

-0.66

lined

-0.65

iqu

-0.64

manager

-0.64

POSITIVE LOGITS

°

1.47

·

1.38

¸

1.32

µ

1.27

¾

1.22

ı

1.17

½

1.15

´

1.15

¼

1.15

Ĭ

1.13

Activations Density 0.003%

words related to geographical locations or specific names

special characters or symbols

No Comments

No Known Activations