INDEX

Explanations

language and phrases indicating alarming, worrying, or distressing situations

oai_token-act-pair · gpt-3.5-turbo

negative descriptors related to disturbing or troubling phenomena

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

ardi

-0.86

glas

-0.79

á

-0.78

arten

-0.77

gerald

-0.76

hement

-0.75

arde

-0.75

elson

-0.75

elsen

-0.73

wright

-0.72

POSITIVE LOGITS

 Revelations

0.90

ly

0.87

ingly

0.87

 revelations

0.77

Trend

0.74

 incidents

0.74

 anomalies

0.71

 noises

0.70

 Trend

0.69

 occurrences

0.68

Activations Density 0.046%

language and phrases indicating alarming, worrying, or distressing situations

negative descriptors related to disturbing or troubling phenomena

No Comments

No Known Activations