INDEX

Explanations

phrases related to an action being influenced or impacted by various factors

oai_token-act-pair · gpt-3.5-turbo

the preposition "by" used in various contexts related to obstacles or challenges

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

LO

-0.76

ettle

-0.72

thal

-0.71

LS

-0.70

llor

-0.69

apest

-0.69

bay

-0.69

WA

-0.68

asy

-0.67

iate

-0.67

POSITIVE LOGITS

 virtue

1.22

products

0.93

 fiat

0.85

laws

0.83

 sheer

0.79

 successive

0.71

 necessity

0.70

 gravity

0.70

 multiplying

0.69

 leaps

0.69

Activations Density 0.133%

phrases related to an action being influenced or impacted by various factors

the preposition "by" used in various contexts related to obstacles or challenges

No Comments

No Known Activations