INDEX

Explanations

phrases related to building, arranging or grouping items together

oai_token-act-pair · gpt-3.5-turbo

references to nests and nesting behavior

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

WAYS

-0.70

Primary

-0.70

VERSION

-0.69

ãĥĨãĤ£

-0.67

 Luther

-0.65

à¤¾

-0.64

 sins

-0.63

 Supplemental

-0.63

 severity

-0.61

×ķ

-0.61

POSITIVE LOGITS

lÃ©

1.01

thal

0.94

lund

0.94

lace

0.93

mate

0.89

eers

0.89

mates

0.89

rone

0.89

aroo

0.85

 nest

0.84

Activations Density 0.026%

phrases related to building, arranging or grouping items together

references to nests and nesting behavior

No Comments

No Known Activations