INDEX

Explanations

questions or inquiries

oai_token-act-pair · gpt-3.5-turbo

question marks, indicating interrogative sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

mental

-0.69

·

-0.68

 limbs

-0.63

 limb

-0.63

¾

-0.63

 pace

-0.62

lp

-0.62

é¾

-0.62

Ĥª

-0.62

weekly

-0.61

POSITIVE LOGITS

 asked

1.07

 inquired

1.04

 asks

1.03

 Asked

0.97

 rhet

0.91

 demanded

0.82

 quizz

0.82

 inqu

0.81

 Questions

0.80

 quer

0.77

Activations Density 0.041%

questions or inquiries

question marks, indicating interrogative sentences

No Comments

No Known Activations