INDEX

Explanations

phrases related to writing activities

oai_token-act-pair · gpt-3.5-turbo

instances of the word "write" in various forms and 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

Ĭ±

-0.82

eger

-0.82

illon

-0.75

alo

-0.74

Unity

-0.73

 ILCS

-0.71

aband

-0.70

agara

-0.69

azar

-0.67

EGA

-0.67

POSITIVE LOGITS

 poems

0.85

writer

0.83

Write

0.80

manship

0.79

 journal

0.79

smanship

0.79

 poem

0.78

writing

0.77

wrote

0.77

writ

0.77

Activations Density 0.033%

phrases related to writing activities

instances of the word "write" in various forms and contexts

No Comments

No Known Activations