INDEX

Explanations

the name "Jennifer"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Jennifer" 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 @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

holders

-0.89

 nomine

-0.77

Interstitial

-0.76

holder

-0.76

dayName

-0.74

 administr

-0.73

 exting

-0.72

Þ

-0.68

 tradem

-0.68

ername

-0.67

POSITIVE LOGITS

 Lopez

1.09

 Lawrence

1.01

issance

0.98

 Walters

0.89

 Mellon

0.88

 Curry

0.86

 Jacobs

0.83

 Crawford

0.82

 Johnston

0.82

 Chen

0.81

Activations Density 0.008%

the name "Jennifer"

occurrences of the name "Jennifer" in various contexts

No Comments

No Known Activations