INDEX

Explanations

words related to lacking or absence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating a deficiency or absence of something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dry

-0.67

escal

-0.64

tainment

-0.63

alty

-0.62

eve

-0.62

dr

-0.60

selves

-0.60

flo

-0.60

Pacific

-0.58

oos

-0.58

POSITIVE LOGITS

lust

1.02

luster

0.88

lessly

0.75

 willpower

0.71

vre

0.70

 miser

0.69

avorite

0.69

 hesitation

0.69

 patience

0.68

minded

0.66

Activations Density 0.024%

words related to lacking or absence

phrases indicating a deficiency or absence of something

No Comments

No Known Activations