INDEX

Explanations

phrases related to similarity or comparison

oai_token-act-pair · gpt-3.5-turbo

comparisons of similarity between different subjects or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

nos

-0.64

unes

-0.54

 trusted

-0.53

onso

-0.52

rection

-0.52

Published

-0.51

Sev

-0.50

achment

-0.50

capital

-0.50

 Physicians

-0.50

POSITIVE LOGITS

to

0.98

 twins

0.82

 thereto

0.78

 enough

0.75

lihood

0.74

ities

0.74

 unto

0.74

ively

0.70

 except

0.68

icut

0.67

Activations Density 0.048%

phrases related to similarity or comparison

comparisons of similarity between different subjects or concepts

No Comments

No Known Activations