INDEX

Explanations

words related to success and achievement

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a negation or refusal

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

uyomi

-0.73

arlane

-0.71

cients

-0.70

rehensive

-0.68

azo

-0.67

Newsletter

-0.63

anut

-0.61

unia

-0.61

 mess

-0.61

igmat

-0.60

POSITIVE LOGITS

Â¢

0.79

elsen

0.68

istan

0.68

 Pulitzer

0.65

 payoff

0.64

 bragging

0.64

itle

0.64

 gladly

0.64

 trophies

0.63

Â¯

0.63

Activations Density 0.128%

words related to success and achievement

phrases indicating a negation or refusal

No Comments

No Known Activations