INDEX

Explanations

phrases indicating someone taking a particular action

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "let's" indicating suggestions or calls to action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eur

-0.79

 Source

-0.71

CVE

-0.67

 Allied

-0.63

ELD

-0.60

 Valkyrie

-0.59

è»

-0.59

 Reef

-0.58

 restraints

-0.58

Creat

-0.57

POSITIVE LOGITS

 pretend

0.86

olve

0.83

itate

0.80

 fulfill

0.80

kaya

0.80

 suppose

0.79

 assume

0.78

 prove

0.78

pecially

0.78

 resolve

0.77

Activations Density 0.030%

phrases indicating someone taking a particular action

the repeated use of the word "let's" indicating suggestions or calls to action

No Comments

No Known Activations