INDEX

Explanations

words related to laps, including actions, items, and concepts with the term "lap" in them

oai_token-act-pair · gpt-3.5-turbo

terms related to laps and related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Flavoring

-0.88

hood

-0.71

xual

-0.71

========

-0.69

hips

-0.68

merce

-0.66

 Marketable

-0.65

============

-0.64

NESS

-0.63

ALLY

-0.62

POSITIVE LOGITS

dogs

1.01

ocobo

0.99

dog

0.97

robe

0.92

olitan

0.90

ipop

0.90

chair

0.89

olit

0.88

agne

0.87

iths

0.86

Activations Density 0.031%

words related to laps, including actions, items, and concepts with the term "lap" in them

terms related to laps and related contexts

No Comments

No Known Activations