INDEX

Explanations

phrases related to uncertainty or lack of information

oai_token-act-pair · gpt-3.5-turbo

terms related to uncertainty or lack of information

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

ugi

-0.63

aurus

-0.63

 broom

-0.62

 redesigned

-0.60

 resil

-0.58

interrupted

-0.57

yip

-0.57

version

-0.55

oise

-0.55

inals

-0.55

POSITIVE LOGITS

yet

0.86

yet

0.85

but

0.83

 owing

0.81

 pending

0.80

.<

0.78

 until

0.76

TBD

0.74

answer

0.74

 definitively

0.74

Activations Density 0.129%

phrases related to uncertainty or lack of information

terms related to uncertainty or lack of information

No Comments

No Known Activations