INDEX

Explanations

words with the suffix "-ly"

oai_token-act-pair · gpt-3.5-turbo

words ending in "ly"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ilater

-0.93

ilogy

-0.74

afety

-0.71

ERA

-0.69

 comprom

-0.67

raviolet

-0.67

ĸļ

-0.66

 Annotations

-0.66

erto

-0.65

irlf

-0.64

POSITIVE LOGITS

rics

0.96

puff

0.94

tics

0.90

ffe

0.85

zed

0.84

upe

0.78

pha

0.78

ph

0.78

cery

0.75

mph

0.74

Activations Density 0.030%

words with the suffix "-ly"

words ending in "ly"

No Comments

No Known Activations