INDEX

Explanations

words ending in "-ation"

oai_token-act-pair · gpt-3.5-turbo

various forms of the suffix "ation," indicating processes, actions, or conditions

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

Negative Logits

inav

-0.79

ãĥ£

-0.73

herty

-0.72

 mosqu

-0.68

soDeliveryDate

-0.68

ilan

-0.67

 opio

-0.66

tails

-0.64

friends

-0.64

ãĥĥãĥī

-0.64

POSITIVE LOGITS

ary

1.52

ally

1.30

naire

1.22

ist

1.17

aries

1.17

hower

1.09

arily

0.99

eering

0.98

ality

0.97

ists

0.96

Activations Density 0.149%

words ending in "-ation"

various forms of the suffix "ation," indicating processes, actions, or conditions

No Known Activations