INDEX

Explanations

discussions of significant events or transformations

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

vertisements

-0.65

urat

-0.64

 helicop

-0.64

ividually

-0.60

abee

-0.60

untarily

-0.59

essor

-0.59

 sacrific

-0.57

arton

-0.56

 challeng

-0.56

POSITIVE LOGITS

 unfolding

0.64

 OnePlus

0.61

 awaits

0.59

0.58

 rebirth

0.56

 involving

0.56

 Ukraine

0.56

 Fukushima

0.55

 unfold

0.55

 lately

0.55

Activations Density 0.460%

discussions of significant events or transformations

No Comments

No Known Activations