INDEX

Explanations

the word "ton" appearing in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to large quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ELD

-0.75

heid

-0.67

Kad

-0.67

 Proceedings

-0.65

rador

-0.64

 Correspond

-0.63

 Telecommunications

-0.63

knit

-0.63

Zot

-0.62

Known

-0.62

POSITIVE LOGITS

Ton

0.90

neau

0.87

umen

0.87

aton

0.84

itionally

0.83

oxic

0.82

 earthqu

0.81

ton

0.80

ne

0.77

nea

0.77

Activations Density 0.012%

the word "ton" appearing in various contexts

references to large quantities or amounts

No Comments

No Known Activations