INDEX

Explanations

mentions of the word "Ace" with varying levels of emphasis

oai_token-act-pair · gpt-3.5-turbo

the brand name "Ace."

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

icity

-0.74

isations

-0.73

arily

-0.72

eners

-0.72

asty

-0.71

ained

-0.71

iversal

-0.70

attribute

-0.70

usalem

-0.69

achu

-0.69

POSITIVE LOGITS

Ace

0.89

 Ventura

0.89

idon

0.80

bay

0.77

 Hardware

0.77

illary

0.74

cean

0.73

vich

0.72

reon

0.65

 Trainer

0.65

Activations Density 0.014%

mentions of the word "Ace" with varying levels of emphasis

the brand name "Ace."

No Comments

No Known Activations