INDEX

Explanations

instances of being subjected to various forms of treatment or processes, often in a negative context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izons

-0.76

redo

-0.69

iability

-0.68

soon

-0.68

 coffers

-0.67

soDeliveryDate

-0.67

idity

-0.67

connected

-0.66

 intending

-0.66

hed

-0.65

POSITIVE LOGITS

 firsthand

0.96

 intense

0.95

 humiliating

0.90

 gunfire

0.88

 ridicule

0.86

 humiliation

0.83

 excruciating

0.82

 brutal

0.82

 barrage

0.81

 harsh

0.79

Activations Density 0.038%

instances of being subjected to various forms of treatment or processes, often in a negative context

No Comments

No Known Activations