INDEX

Explanations

references to warnings or alert messages

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "warning."

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

animate

-0.76

morph

-0.75

anova

-0.73

ophon

-0.72

hedral

-0.71

artney

-0.68

inion

-0.67

tiny

-0.67

atism

-0.67

rencies

-0.65

POSITIVE LOGITS

warning

1.02

 warning

0.90

 Signs

0.89

 warnings

0.89

 Warn

0.88

 Warning

0.86

 disclaimer

0.86

 signs

0.83

warn

0.80

llor

0.78

Activations Density 0.036%

references to warnings or alert messages

occurrences of the word "warning."

No Comments

No Known Activations