INDEX

Explanations

locations or landmarks such as canyons, parks, and roads

oai_token-act-pair · gpt-3.5-turbo

mentions of specific geographical locations or parks

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

encer

-0.87

encers

-0.86

iencies

-0.75

ively

-0.73

ÑĮ

-0.71

ortun

-0.70

enced

-0.70

iveness

-0.70

 Tradable

-0.67

 advoc

-0.67

POSITIVE LOGITS

 Canyon

1.01

 canyon

0.93

lands

0.90

lake

0.89

 Springs

0.88

 Dwell

0.84

 Rapids

0.84

 Creek

0.77

geon

0.77

zilla

0.76

Activations Density 0.013%

locations or landmarks such as canyons, parks, and roads

mentions of specific geographical locations or parks

No Comments

No Known Activations