INDEX

Explanations

references to physical locations or geographical features

oai_token-act-pair · gpt-3.5-turbo

the concept of intersections in various contexts, particularly relating to physical locations and abstract ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

warm

-0.71

apons

-0.70

FORE

-0.66

amina

-0.66

pload

-0.65

ALD

-0.65

GES

-0.64

ULE

-0.64

yss

-0.64

zin

-0.64

POSITIVE LOGITS

 intersection

1.23

 intersections

1.07

 junction

0.88

 intersect

0.86

 Frie

0.79

 rupt

0.74

 Beir

0.71

cross

0.70

 Sakuya

0.70

 crossings

0.70

Activations Density 0.009%

references to physical locations or geographical features

the concept of intersections in various contexts, particularly relating to physical locations and abstract ideas

No Comments

No Known Activations