INDEX

Explanations

proper nouns indicating a position of being the "oldest" or "youngest."

oai_token-act-pair · gpt-3.5-turbo

terms related to age hierarchy, specifically "oldest" and "youngest."

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

IFrame

Link

Negative Logits

rompt

-0.82

bara

-0.81

raltar

-0.75

ued

-0.74

yrinth

-0.73

umen

-0.72

roth

-0.71

ovi

-0.69

phis

-0.69

stri

-0.67

POSITIVE LOGITS

 extant

0.81

 surviving

0.80

 oldest

0.76

 conceivable

0.75

 Greatest

0.74

 imaginable

0.74

 ever

0.73

liest

0.72

 sibling

0.72

iest

0.72

Activations Density 0.013%

proper nouns indicating a position of being the "oldest" or "youngest."

terms related to age hierarchy, specifically "oldest" and "youngest."

No Known Activations