INDEX

Explanations

phrases indicating a reason or purpose

oai_token-act-pair · gpt-3.5-turbo

the demonstrative pronouns "this" and "that."

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

ãĤ§

-0.73

mare

-0.68

cheat

-0.67

ved

-0.64

osterone

-0.64

glers

-0.63

 Activate

-0.62

Cho

-0.62

rien

-0.62

mosp

-0.62

POSITIVE LOGITS

 sake

1.88

 purposes

1.59

 reasons

1.18

 purpose

1.15

ummies

1.09

 foreseeable

0.91

 eternity

0.88

 reason

0.88

umption

0.84

 upcoming

0.83

Activations Density 0.234%

phrases indicating a reason or purpose

the demonstrative pronouns "this" and "that."

No Comments

No Known Activations