INDEX

Explanations

words related to distraction and being distracted

oai_token-act-pair · gpt-3.5-turbo

words related to distraction and deceiving attention

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

iders

-0.73

ITH

-0.64

anne

-0.61

tained

-0.60

 Ibid

-0.59

nai

-0.59

 accepted

-0.58

Ð´

-0.57

gs

-0.57

ept

-0.56

POSITIVE LOGITS

 distract

0.79

 distractions

0.78

 distraction

0.75

 distracted

0.75

ming

0.72

shire

0.71

alus

0.71

ingly

0.70

aline

0.69

 distracting

0.69

Activations Density 0.019%

words related to distraction and being distracted

words related to distraction and deceiving attention

No Comments

No Known Activations