INDEX

Explanations

phrases containing dialogues with speech marks

oai_token-act-pair · gpt-3.5-turbo

punctuation marks, particularly quotation marks in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

»Ĵ

-0.82

İĭ

-0.78

etheless

-0.74

¬¼

-0.69

ramid

-0.68

£ı

-0.67

Ĥª

-0.66

erity

-0.65

²¾

-0.65

Ń·

-0.64

POSITIVE LOGITS

 says

0.97

 reads

0.93

said

0.89

 recalls

0.88

 said

0.85

 replied

0.81

 Said

0.78

 exclaimed

0.78

 whispered

0.78

 murm

0.75

Activations Density 0.107%

phrases containing dialogues with speech marks

punctuation marks, particularly quotation marks in dialogue

No Comments

No Known Activations