INDEX

Explanations

words related to specificity or particularity

oai_token-act-pair · gpt-3.5-turbo

the word "specific" and its variations within different contexts

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

 Feldman

-0.80

ulton

-0.77

 McGee

-0.75

 Tycoon

-0.71

 Alive

-0.70

 largeDownload

-0.66

UP

-0.65

 Kenn

-0.65

 Laur

-0.64

IAN

-0.64

POSITIVE LOGITS

 identifiable

0.99

ities

0.95

 kinds

0.87

 batches

0.87

ively

0.85

izations

0.84

iates

0.84

iations

0.83

 geographic

0.83

wcs

0.83

Activations Density 0.019%

words related to specificity or particularity

the word "specific" and its variations within different contexts

No Comments

No Known Activations