INDEX

Explanations

phrases indicating outreach or communication

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

å£«

-0.78

 Carbuncle

-0.76

 Tsukuyomi

-0.74

asus

-0.65

 reckoning

-0.62

 overrun

-0.61

 rack

-0.61

 occupancy

-0.61

 combustion

-0.59

¥µ

-0.58

POSITIVE LOGITS

stretched

1.06

wards

0.86

 condolences

0.76

 invitations

0.73

via

0.70

reb

0.69

reprene

0.69

 hither

0.68

rils

0.67

felt

0.67

Activations Density 0.010%

phrases indicating outreach or communication

No Comments

No Known Activations