INDEX

Explanations

phrases related to directions and locations

oai_token-act-pair · gpt-3.5-turbo

plural nouns and specific terms related to locations and objects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

KNOWN

-0.78

CHAR

-0.70

atorium

-0.67

FUN

-0.65

emort

-0.65

ISON

-0.64

oÄŁ

-0.64

issance

-0.62

ERAL

-0.60

obo

-0.59

POSITIVE LOGITS

mith

1.16

creen

1.04

pace

1.00

cape

1.00

layer

1.00

ystem

0.96

etting

0.96

hops

0.95

lain

0.94

ucker

0.93

Activations Density 0.215%

phrases related to directions and locations

plural nouns and specific terms related to locations and objects

No Comments

No Known Activations