INDEX

Explanations

interactions between individuals with titles and formal language, suggesting a conversational setting

oai_token-act-pair · gpt-3.5-turbo

conversational phrases that include names and titles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

igen

-0.86

cases

-0.69

 fueling

-0.67

 interchange

-0.67

edition

-0.62

projects

-0.62

 polar

-0.62

 seals

-0.62

 exchanges

-0.60

 suites

-0.60

POSITIVE LOGITS

 Gentleman

0.85

 Disciple

0.82

 Beware

0.81

 beware

0.78

 thank

0.77

 congratulations

0.76

 Dear

0.73

 please

0.72

 Metatron

0.72

 Mistress

0.72

Activations Density 0.248%

interactions between individuals with titles and formal language, suggesting a conversational setting

conversational phrases that include names and titles

No Comments

No Known Activations