INDEX

Explanations

past tense verbs indicating disappearance or removal

oai_token-act-pair · gpt-3.5-turbo

the word "gone" and its variations in context, particularly regarding loss or absence

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

eering

-0.65

FIG

-0.65

 Deity

-0.63

ussen

-0.62

role

-0.61

alist

-0.61

 barr

-0.59

trump

-0.58

advertisement

-0.57

eers

-0.57

POSITIVE LOGITS

 forever

1.00

bye

0.85

 unnoticed

0.83

 overboard

0.81

 viral

0.75

bs

0.74

 limp

0.74

 rogue

0.72

 undone

0.71

bye

0.71

Activations Density 0.032%

past tense verbs indicating disappearance or removal

the word "gone" and its variations in context, particularly regarding loss or absence

No Comments

No Known Activations