INDEX

Explanations

words related to animated content

oai_token-act-pair · gpt-3.5-turbo

terms related to animated films and series

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

orr

-0.85

hoff

-0.78

rank

-0.76

umbing

-0.73

agher

-0.72

yer

-0.72

ledge

-0.71

inness

-0.71

 Lawyers

-0.71

marked

-0.71

POSITIVE LOGITS

GIF

1.02

gif

0.88

agus

0.75

ebted

0.74

ocument

0.74

cember

0.71

atable

0.70

 characters

0.70

 cartoons

0.68

netflix

0.67

Activations Density 0.016%

words related to animated content

terms related to animated films and series

No Comments

No Known Activations