INDEX

Explanations

instances where something is described as either 'short' or 'long'

oai_token-act-pair · gpt-3.5-turbo

adjectives that describe length or extent, such as short and long

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

ROR

-0.65

RIPT

-0.64

 subsequ

-0.63

EMENT

-0.62

MENTS

-0.62

 Realms

-0.59

è¡

-0.59

ä½ľ

-0.57

IONS

-0.56

çīĪ

-0.55

POSITIVE LOGITS

 enough

1.34

founded

1.09

enough

1.03

sighted

1.02

ened

0.98

 Enough

0.97

igned

0.95

listed

0.94

fed

0.94

footed

0.93

Activations Density 0.301%

instances where something is described as either 'short' or 'long'

adjectives that describe length or extent, such as short and long

No Comments

No Known Activations