INDEX

Explanations

mentions of debates or discussions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "argument."

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

eco

-0.74

oho

-0.73

ummer

-0.70

 livest

-0.67

cler

-0.66

ookie

-0.64

appy

-0.63

 sight

-0.62

 stocking

-0.60

engineering

-0.60

POSITIVE LOGITS

uments

1.11

 arguments

1.03

ative

0.94

 argument

0.92

 arguing

0.83

ļéĨĴ

0.82

argument

0.81

ument

0.79

 against

0.78

 persu

0.78

Activations Density 0.024%

mentions of debates or discussions

occurrences of the word "argument."

No Comments

No Known Activations