INDEX

Explanations

repeated patterns or consistencies

oai_token-act-pair · gpt-3.5-turbo

the word "consistently" and similar phrases indicating reliability or frequency

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ster

-0.82

sters

-0.74

 Mour

-0.67

soc

-0.67

eral

-0.65

tein

-0.64

OTOS

-0.63

ja

-0.62

wife

-0.62

Jac

-0.62

POSITIVE LOGITS

ãĤ©

0.81

 outper

0.81

 worshipped

0.77

 conclud

0.76

 rated

0.75

 underestimated

0.75

 impressed

0.73

 maintained

0.72

nces

0.71

 evolve

0.71

Activations Density 0.024%

repeated patterns or consistencies

the word "consistently" and similar phrases indicating reliability or frequency

No Comments

No Known Activations