INDEX

Explanations

phrases and terms related to expressing opinions or beliefs

oai_token-act-pair · gpt-3.5-turbo

references to differing opinions or perspectives

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

wealth

-0.73

cial

-0.73

trap

-0.70

ursed

-0.67

ufact

-0.66

cially

-0.65

breaking

-0.65

period

-0.64

cold

-0.64

dry

-0.64

POSITIVE LOGITS

 views

1.14

 guiActiveUn

1.01

 viewpoints

0.92

 opinions

0.85

ports

0.84

terday

0.83

 viewpoint

0.79

 opin

0.76

 Views

0.73

yip

0.73

Activations Density 0.009%

phrases and terms related to expressing opinions or beliefs

references to differing opinions or perspectives

No Comments

No Known Activations