INDEX

Explanations

brand names and trademarks

oai_token-act-pair · gpt-3.5-turbo

punctuation and special characters in the text

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

 conclud

-0.79

 millenn

-0.77

 condem

-0.70

ilater

-0.68

 comprom

-0.68

 encount

-0.67

attered

-0.67

hran

-0.66

hement

-0.65

 volunte

-0.65

POSITIVE LOGITS

 Detected

0.82

Minecraft

0.76

 Subtle

0.74

 Swarm

0.73

 Fract

0.73

 Scale

0.72

 Basics

0.72

 Euph

0.72

 Emblem

0.71

 Nose

0.70

Activations Density 0.600%

brand names and trademarks

punctuation and special characters in the text

No Comments

No Known Activations