INDEX

Explanations

restaurants or food-related terms

oai_token-act-pair · gpt-3.5-turbo

the word "diner" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

hovah

-0.81

akening

-0.71

isSpecialOrderable

-0.68

gap

-0.65

solid

-0.65

Constructed

-0.64

rouse

-0.64

PLA

-0.64

Kar

-0.64

carry

-0.63

POSITIVE LOGITS

iner

1.28

iners

1.01

throp

0.95

ineries

0.78

lein

0.77

hoe

0.77

naissance

0.74

osaurs

0.73

 offic

0.72

stein

0.72

Activations Density 0.012%

restaurants or food-related terms

the word "diner" in various contexts

No Comments

No Known Activations