INDEX

Explanations

words related to physical barriers or boundaries, specifically fences

oai_token-act-pair · gpt-3.5-turbo

references to fences

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

olute

-0.78

 Monetary

-0.72

orean

-0.70

amus

-0.68

izable

-0.67

olitan

-0.67

Nir

-0.67

alg

-0.67

ISTER

-0.66

entials

-0.64

POSITIVE LOGITS

 fence

1.32

 fences

1.10

 fencing

1.01

ModLoader

0.94

 encl

0.85

 este

0.83

 wart

0.80

 railing

0.80

 perimeter

0.78

 guarding

0.77

Activations Density 0.011%

words related to physical barriers or boundaries, specifically fences

references to fences

No Comments

No Known Activations