INDEX

Explanations

phrases related to passive-aggressive behavior

oai_token-act-pair · gpt-3.5-turbo

language associated with passive-aggressive behavior

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

arya

-0.84

flies

-0.77

ograp

-0.76

AMI

-0.74

ĸļ

-0.70

andum

-0.69

esan

-0.69

akura

-0.67

marks

-0.67

ographers

-0.65

POSITIVE LOGITS

 Passive

0.88

 passive

0.81

 minded

0.81

aggressive

0.81

wd

0.80

comm

0.79

spect

0.75

 aggressive

0.73

ives

0.73

 Perception

0.72

Activations Density 0.034%

phrases related to passive-aggressive behavior

language associated with passive-aggressive behavior

No Comments

No Known Activations