INDEX

Explanations

terms related to cyber threats and attacks

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

alities

-0.74

natureconservancy

-0.72

alties

-0.72

 Aram

-0.71

theless

-0.70

Aad

-0.70

lain

-0.68

hani

-0.67

ulton

-0.67

ulet

-0.66

POSITIVE LOGITS

DoS

1.14

 mitigation

1.03

threat

0.96

 swarm

0.93

 attack

0.90

 attacks

0.88

 amplification

0.86

Attack

0.84

 cancellation

0.83

 prevention

0.83

Activations Density 0.006%

terms related to cyber threats and attacks

No Comments

No Known Activations