INDEX

Explanations

mentions of something being "not new."

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "newness" or the idea that something is not new

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

tein

-0.68

 Winc

-0.65

thora

-0.64

rotein

-0.63

unk

-0.62

regate

-0.61

fax

-0.60

prus

-0.59

iffs

-0.59

ignt

-0.58

POSITIVE LOGITS

rums

0.77

 beginnings

0.72

actionDate

0.71

owan

0.70

lishes

0.69

liest

0.69

 infancy

0.68

born

0.67

ORN

0.65

yk

0.64

Activations Density 0.063%

mentions of something being "not new."

references to the concept of "newness" or the idea that something is not new

No Comments

No Known Activations