INDEX

Explanations

words related to changes or transformations

oai_token-act-pair · gpt-3.5-turbo

instances of the word "transform" and variations related to changing or altering something

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Continued

-0.74

 quer

-0.71

held

-0.69

 addressed

-0.66

given

-0.66

 elic

-0.66

 asked

-0.65

 ascert

-0.65

 undersc

-0.64

aton

-0.64

POSITIVE LOGITS

 transform

1.64

 fade

1.53

 sail

1.53

 rotate

1.48

 flee

1.46

 weave

1.45

 weigh

1.44

 explode

1.41

 crawl

1.39

 choke

1.37

Activations Density 0.078%

words related to changes or transformations

instances of the word "transform" and variations related to changing or altering something

No Comments

No Known Activations