INDEX

Explanations

lines of text ending with a specific character as indicated by the colon with high activation values

oai_token-act-pair · gpt-3.5-turbo

sequences of punctuation marks and structured text elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Leaks

-0.78

 ingred

-0.70

soDeliveryDate

-0.68

 hemor

-0.67

æ©

-0.66

 pestic

-0.65

 principals

-0.65

ensibly

-0.64

 exting

-0.64

 Palestin

-0.61

POSITIVE LOGITS

 âĨĳ

0.89

Show

0.76

 Adding

0.69

 Originally

0.68

Cly

0.68

 Interesting

0.66

itars

0.65

leon

0.64

Originally

0.64

 inherit

0.63

Activations Density 0.071%

lines of text ending with a specific character as indicated by the colon with high activation values

sequences of punctuation marks and structured text elements

No Comments

No Known Activations