INDEX

Explanations

mentions of elephants

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "elephant" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

hub

-0.82

Hub

-0.81

oplan

-0.77

bp

-0.74

Hub

-0.73

bnb

-0.72

 hubs

-0.72

 burgers

-0.71

bsp

-0.71

wcs

-0.70

POSITIVE LOGITS

Ele

3.33

Ele

2.40

ele

2.37

 Elephant

1.50

Ð´

1.44

ELE

1.33

 elephants

1.29

ele

1.22

 Alexandra

1.12

 elephant

1.10

Activations Density 0.040%

mentions of elephants

occurrences of the word "elephant" and its variations

No Comments

No Known Activations