INDEX

Explanations

instances of corporate entities and their relationships in the context of specific actions or events

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

 endings

-0.83

thirds

-0.76

imester

-0.75

hemer

-0.74

 disse

-0.72

sectional

-0.72

pleasant

-0.72

xual

-0.72

ilege

-0.71

 accompan

-0.71

POSITIVE LOGITS

 Motorola

1.03

 Sony

1.00

 Siem

0.99

 Alibaba

0.98

 Amazon

0.98

IBM

0.97

 Microsoft

0.96

Amazon

0.96

 Cosponsors

0.95

 Warner

0.95

Activations Density 0.125%

instances of corporate entities and their relationships in the context of specific actions or events

No Comments

No Known Activations