INDEX

Explanations

phrases with the word "near"

oai_token-act-pair · gpt-3.5-turbo

repetitions of the definite article "the" in reference to proximity to geographical locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 alone

-0.80

rix

-0.79

 thereafter

-0.78

fully

-0.77

ful

-0.76

ocument

-0.75

RIC

-0.74

IQ

-0.71

Quantity

-0.71

among

-0.70

POSITIVE LOGITS

 entrance

1.27

 shore

1.12

 edge

1.10

 intersection

1.09

 entrances

1.09

 nearest

1.07

 shores

1.06

 center

1.03

 coast

1.01

 finish

0.98

Activations Density 0.122%

phrases with the word "near"

repetitions of the definite article "the" in reference to proximity to geographical locations

No Comments

No Known Activations