INDEX

Explanations

superlatives or emphatic descriptions like "strongest," "best," and "biggest."

oai_token-act-pair · gpt-3.5-turbo

superlatives or words that denote high quality or significance

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

keleton

-0.81

obook

-0.79

ategory

-0.75

fecture

-0.75

ope

-0.74

ologue

-0.73

matter

-0.73

hyde

-0.73

utenant

-0.72

rium

-0.70

POSITIVE LOGITS

 avenues

1.12

 pillars

1.10

 fronts

1.10

 examples

1.10

 aspects

1.09

 instances

1.07

 facets

1.05

 occasions

1.05

 topics

1.03

 professions

1.01

Activations Density 0.144%

superlatives or emphatic descriptions like "strongest," "best," and "biggest."

superlatives or words that denote high quality or significance

No Comments

No Known Activations