INDEX

Explanations

phrases related to making changes or adjustments

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a reference to quantities or amounts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

actionDate

-0.68

swer

-0.65

ifted

-0.62

ppers

-0.60

mbudsman

-0.59

 envy

-0.59

masters

-0.58

Ã®

-0.58

 emergence

-0.57

 planners

-0.57

POSITIVE LOGITS

 aspects

0.81

ones

0.77

utations

0.76

 existing

0.76

 portion

0.72

thin

0.70

 portions

0.70

 unwanted

0.70

aciously

0.69

 previously

0.69

Activations Density 0.323%

phrases related to making changes or adjustments

phrases that indicate a reference to quantities or amounts

No Comments

No Known Activations