INDEX

Explanations

phrases related to computer processors and technological terms

oai_token-act-pair · gpt-3.5-turbo

references to specific scientific terms or entities, particularly related to technology and measurements

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 skelet

-0.85

Reviewer

-0.82

 Palestin

-0.77

 plur

-0.74

 Thumbnails

-0.71

ACTED

-0.70

 Petr

-0.69

Catal

-0.64

utics

-0.63

phabet

-0.63

POSITIVE LOGITS

tz

1.10

arella

0.89

eta

0.87

weet

0.86

oning

0.84

ky

0.82

hao

0.80

ania

0.80

apest

0.79

enger

0.79

Activations Density 0.008%

phrases related to computer processors and technological terms

references to specific scientific terms or entities, particularly related to technology and measurements

No Comments

No Known Activations