INDEX

Explanations

terms associated with hardship or difficult circumstances

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

glomer

-0.70

tein

-0.69

zyme

-0.66

 logos

-0.66

 Prediction

-0.62

ombs

-0.62

 nucle

-0.62

 weights

-0.61

 confir

-0.61

 certific

-0.59

POSITIVE LOGITS

 plight

1.06

ously

0.94

retched

0.78

 plag

0.77

ingly

0.73

oire

0.73

dden

0.72

ours

0.71

pid

0.68

iful

0.67

Activations Density 0.022%

terms associated with hardship or difficult circumstances

No Comments

No Known Activations