INDEX

Explanations

images or pictures mentioned in a text

oai_token-act-pair · gpt-3.5-turbo

references to content located below in the text

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

ãĥı

-0.85

MM

-0.72

ãĥĥãĥĪ

-0.67

ãĤ£

-0.66

POSE

-0.65

éŃĶ

-0.64

æ©

-0.64

olid

-0.64

=-=-=-=-=-=-=-=-

-0.63

oka

-0.62

POSITIVE LOGITS

ground

0.90

ebin

0.84

below

0.78

eatures

0.78

 below

0.70

tics

0.70

 tradem

0.68

 summar

0.66

irement

0.66

 veter

0.65

Activations Density 0.023%

images or pictures mentioned in a text

references to content located below in the text

No Comments

No Known Activations