INDEX

Explanations

references to rabbits

oai_token-act-pair · gpt-3.5-turbo

references to rabbits and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

igmat

-0.73

gow

-0.72

ructure

-0.70

ician

-0.69

rators

-0.68

rylic

-0.68

ribute

-0.68

omething

-0.67

orship

-0.67

raints

-0.67

POSITIVE LOGITS

 Rabbit

1.12

MQ

1.08

 rabbit

1.02

meat

0.89

 Hole

0.87

abbit

0.85

 rabbits

0.85

 Nest

0.83

fish

0.80

 Hunt

0.80

Activations Density 0.008%

references to rabbits

references to rabbits and related terms

No Comments

No Known Activations