INDEX

Explanations

terms related to the physical positioning or placement of objects or entities

oai_token-act-pair · gpt-3.5-turbo

terms related to spatial arrangement or placement

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

ebook

-0.98

displayText

-0.92

ilee

-0.90

vous

-0.88

bey

-0.86

burn

-0.78

cus

-0.76

ilk

-0.76

bies

-0.73

olla

-0.70

POSITIVE LOGITS

eering

0.85

 positions

0.84

 position

0.84

 coordinates

0.81

 locations

0.79

 Position

0.78

 latitude

0.76

 Sensor

0.73

aution

0.73

 location

0.72

Activations Density 0.050%

terms related to the physical positioning or placement of objects or entities

terms related to spatial arrangement or placement

No Comments

No Known Activations