INDEX

Explanations

references to the term "Mad" 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 @ 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

OPLE

-0.85

chnology

-0.80

 Vaugh

-0.74

çĦ

-0.72

IDER

-0.71

 sight

-0.71

kefeller

-0.70

LECT

-0.69

conservancy

-0.68

×Ļ×

-0.67

POSITIVE LOGITS

hya

1.08

agascar

1.04

oka

1.04

eline

1.02

ras

1.01

der

0.95

urai

0.95

onna

0.94

rid

0.93

roid

0.92

Activations Density 0.006%

references to the term "Mad" in various contexts

No Comments

No Known Activations