INDEX

Explanations

proper nouns or specific names mentioned in the text

oai_token-act-pair · gpt-3.5-turbo

instances of the word "naming" and its contextual usage

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

ilit

-0.66

emp

-0.63

 Approximately

-0.62

 countered

-0.61

renched

-0.61

aft

-0.61

lite

-0.61

hang

-0.60

fi

-0.59

moderate

-0.59

POSITIVE LOGITS

 naming

3.98

 names

1.64

 branding

1.53

Names

1.49

 rename

1.47

 spelling

1.47

 Names

1.44

 numbering

1.43

 name

1.41

 mentioning

1.39

Activations Density 0.013%

proper nouns or specific names mentioned in the text

instances of the word "naming" and its contextual usage

No Comments

No Known Activations