INDEX

Explanations

references to the "Resident Evil" franchise

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

agall

-0.77

igate

-0.76

matically

-0.74

aquin

-0.74

dropping

-0.72

achy

-0.68

ickr

-0.67

ounced

-0.65

 strengthening

-0.65

trl

-0.65

POSITIVE LOGITS

iva

0.88

 Dead

0.79

 Squad

0.77

 Genius

0.76

 Pinball

0.74

 Spiegel

0.74

 Virus

0.74

 Outbreak

0.74

 Trooper

0.74

 Warlock

0.74

Activations Density 0.006%

references to the "Resident Evil" franchise

No Comments

No Known Activations