INDEX

Explanations

words related to the term "rogue"

oai_token-act-pair · gpt-3.5-turbo

the word "rog" or related variants, which may indicate a focus on themes of deception or trickery

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

birth

-0.73

 goodbye

-0.71

aved

-0.67

AAP

-0.63

âķĲ

-0.61

 spaced

-0.61

 ranks

-0.60

creen

-0.59

 Teresa

-0.58

 birth

-0.57

POSITIVE LOGITS

raphic

1.35

raphics

1.21

raph

1.11

allery

1.10

aming

1.02

rams

0.98

roup

0.97

adier

0.96

ues

0.96

atory

0.95

Activations Density 0.016%

words related to the term "rogue"

the word "rog" or related variants, which may indicate a focus on themes of deception or trickery

No Comments

No Known Activations