INDEX

Explanations

phrases related to food items or components

oai_token-act-pair · gpt-3.5-turbo

terms related to the Earth's crust and its characteristics

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

FN

-0.69

 PowerPoint

-0.68

 Watts

-0.67

FN

-0.67

ctions

-0.67

ulton

-0.66

 Kamp

-0.66

KNOWN

-0.61

 Grassley

-0.61

 Glob

-0.60

POSITIVE LOGITS

 crust

1.27

ace

1.04

alis

1.00

artisan

1.00

ozo

0.94

acea

0.93

acies

0.91

ules

0.88

al

0.87

oly

0.86

Activations Density 0.011%

phrases related to food items or components

terms related to the Earth's crust and its characteristics

No Comments

No Known Activations