INDEX

Explanations

words ending in "-ation"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "at" 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

 Tsukuyomi

-0.77

ADE

-0.72

ONSORED

-0.66

Rogue

-0.64

 destro

-0.62

 Bangl

-0.61

 forks

-0.60

Xie

-0.60

 Paula

-0.60

 Choi

-0.60

POSITIVE LOGITS

abase

1.01

hetically

0.97

istical

0.96

rix

0.94

hemat

0.94

uitous

0.93

ting

0.92

istics

0.91

roph

0.88

rice

0.87

Activations Density 0.023%

words ending in "-ation"

instances of the word "at" in various contexts

No Comments

No Known Activations