INDEX

Explanations

mentions or variations of the word "Worm"

oai_token-act-pair · gpt-3.5-turbo

references to worms, particularly in various contexts related to health and biology

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uate

-0.75

tera

-0.74

iating

-0.74

afort

-0.71

usher

-0.70

undai

-0.69

culated

-0.68

orically

-0.68

uations

-0.67

owered

-0.67

POSITIVE LOGITS

hole

1.22

worm

1.10

holes

1.02

worms

0.97

nesday

0.89

bare

0.85

tie

0.84

 Hole

0.81

pn

0.81

swick

0.80

Activations Density 0.038%

mentions or variations of the word "Worm"

references to worms, particularly in various contexts related to health and biology

No Comments

No Known Activations