INDEX

Explanations

occurrences of specific names and titles in a context involving arrest or law enforcement

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

torch.float32

Hook Point

blocks.8.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

Tyr

-0.89

 Rece

-0.81

 Depot

-0.77

 Tomato

-0.75

-0.74

tyr

-0.73

 Betty

-0.73

$$$$

-0.68

 sher

-0.68

 predicate

-0.67

POSITIVE LOGITS

ong

1.51

ang

1.42

ongs

1.23

ANG

1.15

angs

1.09

ONG

1.07

onga

1.07

yang

1.04

ung

1.00

ANGE

0.99

Activations Density 0.069%

occurrences of specific names and titles in a context involving arrest or law enforcement

No Comments

No Known Activations