INDEX

Explanations

words related to identification or labeling

oai_token-act-pair · gpt-3.5-turbo

phrases indicating identification or attribution

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

 recons

-0.67

 reinstated

-0.65

ETF

-0.62

 manif

-0.59

uation

-0.58

 Investig

-0.58

 seeded

-0.57

 Fund

-0.57

 contacted

-0.56

 destined

-0.56

POSITIVE LOGITS

onyms

0.80

¥µ

0.80

Ĥª

0.75

ä½¿

0.70

Ĭ±

0.70

advertisement

0.70

otle

0.69

ãĤ´ãĥ³

0.67

OTOS

0.67

name

0.66

Activations Density 0.145%

words related to identification or labeling

phrases indicating identification or attribution

No Comments

No Known Activations