INDEX

Explanations

phrases related to official statements or reports

oai_token-act-pair · gpt-3.5-turbo

repeated instances of the word "the."

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

izons

-0.73

illion

-0.71

Its

-0.70

OTA

-0.70

ambo

-0.67

oscope

-0.67

spell

-0.66

dale

-0.66

rape

-0.65

terday

-0.65

POSITIVE LOGITS

 easiest

0.94

 strongest

0.73

 impossible

0.72

 raining

0.71

 uphill

0.71

 safest

0.71

 customary

0.69

 usual

0.68

 hardest

0.68

 simplest

0.66

Activations Density 0.140%

phrases related to official statements or reports

repeated instances of the word "the."

No Comments

No Known Activations