INDEX

Explanations

words related to explicit statements or instructions

oai_token-act-pair · gpt-3.5-turbo

phrases that mention explicitness or clarity in statements

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

 Tycoon

-0.87

nesota

-0.78

«ĺ

-0.77

Squ

-0.77

STON

-0.72

rug

-0.71

 Royale

-0.70

busters

-0.70

ADS

-0.68

Score

-0.67

POSITIVE LOGITS

 deline

0.81

 guiActiveUn

0.79

 explicit

0.79

ities

0.78

 disclaim

0.77

 textual

0.77

 explicitly

0.77

 disav

0.75

 prohibitions

0.75

 repud

0.73

Activations Density 0.030%

words related to explicit statements or instructions

phrases that mention explicitness or clarity in statements

No Comments

No Known Activations