INDEX

Explanations

questions or prompts related to asking about a next action or step

oai_token-act-pair · gpt-3.5-turbo

questions or inquiries about future developments or outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

JM

-0.76

eds

-0.73

yers

-0.70

mens

-0.69

ords

-0.69

reci

-0.67

unks

-0.67

Day

-0.67

Interstitial

-0.66

FN

-0.66

POSITIVE LOGITS

 exactly

0.81

 separates

0.79

 happens

0.77

 distinguishes

0.75

 else

0.74

 happened

0.73

pload

0.69

 does

0.69

!?

0.68

 redes

0.68

Activations Density 0.069%

questions or prompts related to asking about a next action or step

questions or inquiries about future developments or outcomes

No Comments

No Known Activations