INDEX

Explanations

mentions of brand identity or logo creation

oai_token-act-pair · gpt-3.5-turbo

topics related to marketing and branding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

çīĪ

-0.65

REDACTED

-0.61

 Volcano

-0.57

adel

-0.56

isine

-0.55

(@

-0.54

enegger

-0.53

anooga

-0.53

_.

-0.51

issance

-0.51

POSITIVE LOGITS

 themselves

0.86

 differently

0.73

 specialize

0.73

 excessively

0.71

 tend

0.70

entimes

0.70

 smaller

0.67

 seldom

0.66

 nowadays

0.66

 sometimes

0.65

Activations Density 1.250%

mentions of brand identity or logo creation

topics related to marketing and branding

No Comments

No Known Activations