INDEX

Explanations

numbers used for rounding

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Round" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

natureconservancy

-0.75

iments

-0.73

 mathemat

-0.68

ettel

-0.68

ufact

-0.68

ionage

-0.67

orship

-0.66

 nurt

-0.65

phrine

-0.63

acca

-0.63

POSITIVE LOGITS

about

1.28

abouts

1.27

trip

1.18

table

1.15

ups

0.99

rob

0.95

worms

0.91

up

0.88

backs

0.86

stad

0.86

Activations Density 0.030%

numbers used for rounding

occurrences of the word "Round" and its variations

No Comments

No Known Activations