INDEX

Explanations

the word "realize" in different contexts

oai_token-act-pair · gpt-3.5-turbo

instances of the word "realize" and its variations to detect moments of awareness or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ĪĴ

-0.83

picking

-0.70

 clipboard

-0.69

 wrists

-0.68

oil

-0.66

reen

-0.64

cgi

-0.63

 helmets

-0.63

ciating

-0.62

conservancy

-0.62

POSITIVE LOGITS

ledged

0.86

 realise

0.83

 realize

0.80

REAM

0.80

âĶģ

0.77

ISION

0.76

urities

0.75

 realizes

0.75

actly

0.75

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.75

Activations Density 0.032%

the word "realize" in different contexts

instances of the word "realize" and its variations to detect moments of awareness or understanding

No Comments

No Known Activations