INDEX

Explanations

locations and geographic references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

selves

-0.81

tackle

-0.78

onym

-0.76

ror

-0.75

ãĤ¯

-0.74

angible

-0.71

rahim

-0.70

matic

-0.70

work

-0.69

sheet

-0.67

POSITIVE LOGITS

 County

1.16

 Gardens

0.92

 City

0.91

 Airport

0.91

 Resort

0.87

 Springs

0.87

 Municipal

0.87

 Boulevard

0.86

 Unified

0.86

 Supervisor

0.85

Activations Density 0.067%

locations and geographic references

No Comments

No Known Activations