INDEX

Explanations

mentions of reptiles

oai_token-act-pair · gpt-3.5-turbo

terms related to reptiles and lizards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

Interstitial

-0.71

 Morse

-0.70

WAY

-0.67

ulton

-0.66

 Commonwealth

-0.66

URI

-0.66

viation

-0.66

ADS

-0.64

 Hemp

-0.63

âĸ¬

-0.63

POSITIVE LOGITS

 rept

1.32

 reptiles

1.24

 lizard

1.14

 Rept

1.13

ilian

1.08

afort

1.04

 turtles

1.01

 crocod

0.98

brates

0.95

osaurs

0.90

Activations Density 0.012%

mentions of reptiles

terms related to reptiles and lizards

No Comments

No Known Activations