INDEX

Explanations

phrases or words indicating a sequence or order, specifically the word "Second" with a high activation value

oai_token-act-pair · gpt-3.5-turbo

phrases or words indicating a sequence or ranking

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

ga

-0.79

isconsin

-0.65

Sab

-0.63

pen

-0.63

renheit

-0.60

iesta

-0.58

nas

-0.58

IDA

-0.57

 liter

-0.56

ihar

-0.56

POSITIVE LOGITS

 secondly

0.75

 alternatively

0.72

appropriately

0.72

 conclud

0.69

 importantly

0.68

 wors

0.68

 worms

0.64

 Artifact

0.62

 cynicism

0.62

 surpr

0.61

Activations Density 0.115%

phrases or words indicating a sequence or order, specifically the word "Second" with a high activation value

phrases or words indicating a sequence or ranking

No Comments

No Known Activations