INDEX

Explanations

locations or places near borders

oai_token-act-pair · gpt-3.5-turbo

the word "the" or phrases that include it frequently, indicating a focus on definite articles in descriptive contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 anew

-0.74

rix

-0.70

frey

-0.69

fully

-0.68

ardi

-0.66

 thereafter

-0.65

ophobia

-0.64

eson

-0.64

 indeed

-0.64

 distinguishes

-0.63

POSITIVE LOGITS

 entrance

1.09

 horizon

0.99

 periphery

0.98

 outskirts

0.97

 nearest

0.95

 main

0.94

 walls

0.92

 town

0.90

 intersection

0.89

 perimeter

0.89

Activations Density 0.217%

locations or places near borders

the word "the" or phrases that include it frequently, indicating a focus on definite articles in descriptive contexts

No Comments

No Known Activations