INDEX

Explanations

words related to uniformity or things being the same across different instances

oai_token-act-pair · gpt-3.5-turbo

instances of the word "uniform" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

heimer

-0.92

UD

-0.84

×Ļ×

-0.80

=-=-=-=-

-0.79

=-=-=-=-=-=-=-=-

-0.74

à

-0.74

slow

-0.73

ï¸

-0.73

udic

-0.72

udder

-0.72

POSITIVE LOGITS

 uniform

1.05

 uniforms

1.02

iating

1.00

ially

0.92

itarian

0.92

ity

0.92

iated

0.90

 insign

0.87

 attire

0.86

 worn

0.85

Activations Density 0.009%

words related to uniformity or things being the same across different instances

instances of the word "uniform" and its variations

No Comments

No Known Activations