INDEX

Explanations

terms related to national security

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

amaz

-0.84

Blocks

-0.81

oven

-0.77

unt

-0.76

Torrent

-0.76

bare

-0.76

chrom

-0.74

ken

-0.74

 Refresh

-0.73

 Niet

-0.73

POSITIVE LOGITS

 adviser

1.10

 advisor

1.07

 Advisor

0.91

 Adviser

0.90

 apparatus

0.89

 implications

0.89

 advisors

0.87

 emergencies

0.85

 interests

0.85

 advisers

0.84

Activations Density 0.024%

terms related to national security

No Comments

No Known Activations