INDEX

Explanations

phrases related to hard work and effort

oai_token-act-pair · gpt-3.5-turbo

the word "hard" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ript

-0.77

 Inspector

-0.72

entric

-0.71

 Mens

-0.69

uality

-0.69

 Volt

-0.68

ARDIS

-0.65

amera

-0.65

itutional

-0.65

 Nest

-0.64

POSITIVE LOGITS

ãĥīãĥ©

0.96

ball

0.92

balls

0.88

coded

0.83

disk

0.82

wired

0.81

drive

0.80

cover

0.80

dri

0.80

 hard

0.78

Activations Density 0.033%

phrases related to hard work and effort

the word "hard" in various contexts

No Comments

No Known Activations