INDEX

Explanations

proper nouns and associated descriptors such as names, brands, and titles

oai_token-act-pair · gpt-3.5-turbo

names of individuals or entities associated with achievements or recognition

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

icol

-0.75

osa

-0.72

 Gutenberg

-0.72

Newsletter

-0.70

hack

-0.68

alin

-0.67

)|

-0.67

oller

-0.66

olog

-0.66

Correction

-0.65

POSITIVE LOGITS

 nevertheless

1.11

 nonetheless

1.07

 meticulously

0.91

 poised

0.89

 tirelessly

0.86

 boldly

0.85

 irresist

0.85

 unmist

0.83

 effortlessly

0.83

 relentlessly

0.83

Activations Density 0.528%

proper nouns and associated descriptors such as names, brands, and titles

names of individuals or entities associated with achievements or recognition

No Known Activations