INDEX

Explanations

expressions of doubt or uncertainty about capability or knowledge

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

soType

-0.79

 unspecified

-0.68

è¦ļéĨĴ

-0.66

¿½

-0.66

ENGTH

-0.65

stre

-0.65

FIN

-0.62

 Lawn

-0.61

è£ħ

-0.60

 Maiden

-0.59

POSITIVE LOGITS

 necessarily

1.28

 bother

0.99

 themselves

0.98

 bothered

0.97

 seem

0.96

 realize

0.94

 appreciate

0.92

 hesitate

0.91

 readily

0.90

 realise

0.89

Activations Density 0.122%

expressions of doubt or uncertainty about capability or knowledge

No Comments

No Known Activations