INDEX

Explanations

words related to warnings or commands that evoke specific reactions

oai_token-act-pair · gpt-3.5-turbo

terms related to triggers and their significance in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apest

-0.83

ensable

-0.75

hemat

-0.73

esan

-0.73

egal

-0.72

ographies

-0.71

jri

-0.70

apolis

-0.70

ately

-0.68

atography

-0.68

POSITIVE LOGITS

 warnings

1.02

 triggers

0.96

 triggering

0.94

 trigger

0.91

trigger

0.87

 alerts

0.82

happy

0.81

 warning

0.79

 triggered

0.78

 alert

0.77

Activations Density 0.038%

words related to warnings or commands that evoke specific reactions

terms related to triggers and their significance in various contexts

No Comments

No Known Activations