INDEX

Explanations

phrases related to toxicology and medical terminology

oai_token-act-pair · gpt-3.5-turbo

the word "to" 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

iHUD

-0.81

mble

-0.69

 resemb

-0.67

 exceptions

-0.66

soDeliveryDate

-0.66

 appropri

-0.64

 interests

-0.63

busters

-0.63

 leases

-0.62

ancies

-0.62

POSITIVE LOGITS

ilet

1.47

ffee

1.00

pping

1.00

pped

0.99

oth

0.98

ppers

0.95

othy

0.92

pper

0.91

ques

0.85

ppo

0.84

Activations Density 0.042%

phrases related to toxicology and medical terminology

the word "to" in various contexts

No Comments

No Known Activations