INDEX

Explanations

the phrase "first and foremost."

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "and."

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

ADVERTISEMENT

-0.78

ãĤ§

-0.78

wake

-0.73

-0.71

:(

-0.70

ONSORED

-0.68

IRE

-0.67

BIP

-0.65

 Toast

-0.64

speech

-0.64

POSITIVE LOGITS

rogen

1.04

rogens

1.03

 consequently

0.93

 therefore

0.90

 foremost

0.80

 awaited

0.78

 then

0.76

 possibly

0.76

chard

0.75

 moreover

0.74

Activations Density 0.231%

the phrase "first and foremost."

the repeated use of the word "and."

No Comments

No Known Activations