INDEX

Explanations

words related to characters and character development

oai_token-act-pair · gpt-3.5-turbo

references to character-driven narratives and character attributes in storytelling

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

 forb

-0.70

consumer

-0.67

lass

-0.66

ornia

-0.62

é¾įå¥ĳå£«

-0.62

 issuance

-0.61

 rainy

-0.61

 Contents

-0.61

abus

-0.60

utsche

-0.59

POSITIVE LOGITS

 whom

0.78

POV

0.77

ouver

0.77

ovie

0.69

ãĤ¨ãĥ«

0.67

 Masquerade

0.66

played

0.66

reau

0.65

 PACs

0.63

ikuman

0.62

Activations Density 0.625%

words related to characters and character development

references to character-driven narratives and character attributes in storytelling

No Comments

No Known Activations