INDEX

Explanations

words related to a specific surname

oai_token-act-pair · gpt-3.5-turbo

the word "de" 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 @ 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

allery

-0.92

ĸļ

-0.74

hips

-0.68

 tremend

-0.66

iott

-0.65

atform

-0.65

icals

-0.64

orsi

-0.64

olicy

-0.64

iggins

-0.64

POSITIVE LOGITS

legate

1.24

ploy

1.21

leted

1.20

legates

1.19

utsche

1.18

hyde

1.07

cember

1.06

vel

0.98

cker

0.98

VICE

0.96

Activations Density 0.015%

words related to a specific surname

the word "de" in various contexts

No Comments

No Known Activations