INDEX

Explanations

words related to logos or corporate branding

oai_token-act-pair · gpt-3.5-turbo

references to logos

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

kus

-0.78

neau

-0.74

Ago

-0.69

theless

-0.69

hower

-0.68

astern

-0.68

hurst

-0.67

 Lank

-0.67

charges

-0.65

auld

-0.65

POSITIVE LOGITS

 logos

1.03

 logo

0.94

 Logo

0.90

 Doodle

0.87

plates

0.76

 slogan

0.75

tag

0.73

 branding

0.72

 styling

0.71

inates

0.70

Activations Density 0.047%

words related to logos or corporate branding

references to logos

No Comments

No Known Activations