INDEX

Explanations

variations of the word "drop."

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

eur

-0.87

iola

-0.72

gregation

-0.69

urally

-0.67

heid

-0.64

ãĢĳ

-0.63

"]=>

-0.63

eering

-0.61

ItemTracker

-0.61

orst

-0.61

POSITIVE LOGITS

 jaws

1.01

 hints

0.98

kick

0.96

 leaflets

0.90

 bombs

0.86

 acid

0.85

 bombshell

0.82

owship

0.77

 overboard

0.77

down

0.76

Activations Density 0.029%

variations of the word "drop."

No Comments

No Known Activations