INDEX

Explanations

instances where actions are being attributed to a group of people

oai_token-act-pair · gpt-3.5-turbo

the verb "are" in various contexts, indicating ongoing actions or states

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Achieve

-0.76

 Replacement

-0.70

 Implementation

-0.69

 srfAttach

-0.67

 belongs

-0.67

 Sacrifice

-0.66

poral

-0.66

 Gutenberg

-0.66

itures

-0.65

izational

-0.64

POSITIVE LOGITS

 wondering

1.32

 clam

1.31

 outraged

1.31

 alarmed

1.28

 scrambling

1.25

 appalled

1.24

 worried

1.23

 complaining

1.22

 wary

1.19

 skeptical

1.19

Activations Density 0.206%

instances where actions are being attributed to a group of people

the verb "are" in various contexts, indicating ongoing actions or states

No Comments

No Known Activations