INDEX

Explanations

The neuron looks for text prompting the reader to read more information

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a desire for additional information or to read more

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

cffffcc

-0.75

©¶æ¥µ

-0.63

alties

-0.62

cknowled

-0.61

orously

-0.60

 gest

-0.60

ochem

-0.59

ħĭ

-0.58

 neither

-0.58

 seams

-0.58

POSITIVE LOGITS

 VIDEOS

0.99

 âĨĴ

0.81

 âĢº

0.79

 âĸº

0.79

>>

0.78

>>

0.77

 Â»

0.77

>>>

0.76

<|endoftext|>

0.71

Â»

0.71

Activations Density 0.033%

The neuron looks for text prompting the reader to read more information

phrases indicating a desire for additional information or to read more

No Comments

No Known Activations