INDEX

Explanations

written statements that introduce a new point or emphasize a specific action

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate questions or prompts for further discussion

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

anchester

-0.75

ignt

-0.66

 softened

-0.66

daq

-0.65

rican

-0.64

emies

-0.63

 certific

-0.63

byter

-0.62

 neighb

-0.61

 manoeuv

-0.60

POSITIVE LOGITS

 namely

1.16

 Cosmos

0.78

INS

0.73

0000000000000000

0.67

ãĢĳ

0.66

TEXTURE

0.66

BOOK

0.65

ENGTH

0.64

 graphene

0.63

roma

0.62

Activations Density 0.378%

written statements that introduce a new point or emphasize a specific action

phrases that indicate questions or prompts for further discussion

No Comments

No Known Activations