INDEX

Explanations

nouns related to various events or incidents

oai_token-act-pair · gpt-3.5-turbo

objects or entities involved in various types of activities or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

rawdownloadcloneembedreportprint

-0.88

ï¸ı

-0.76

ernels

-0.76

 Flavoring

-0.75

aughs

-0.75

 VIDEOS

-0.73

}:

-0.72

izons

-0.72

 actionGroup

-0.71

}}}

-0.71

POSITIVE LOGITS

 dubbed

1.01

 believed

0.96

 purportedly

0.95

 deemed

0.95

 belonging

0.94

 containing

0.94

 alleging

0.92

 allegedly

0.91

 designed

0.90

 destined

0.90

Activations Density 0.405%

nouns related to various events or incidents

objects or entities involved in various types of activities or events

No Comments

No Known Activations