INDEX

Explanations

adjectives and nouns related to negative situations

oai_token-act-pair · gpt-3.5-turbo

phrases indicating potential outcomes or consequences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Downloadha

-0.81

ilian

-0.72

claim

-0.71

agree

-0.70

ystem

-0.67

emon

-0.67

urus

-0.66

 allegedly

-0.63

formerly

-0.63

obia

-0.63

POSITIVE LOGITS

 boon

1.00

 next

0.98

 tomorrow

0.95

 someday

0.92

 sooner

0.86

 soon

0.84

 beneficiary

0.77

 forever

0.77

 fruitful

0.77

Activations Density 0.246%

adjectives and nouns related to negative situations

phrases indicating potential outcomes or consequences

No Comments

No Known Activations