INDEX

Explanations

phrases related to government actions and responsibilities

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

çīĪ

-0.61

 aback

-0.60

ĸļ

-0.60

 surpr

-0.60

availability

-0.60

 reluct

-0.59

Ĭ±

-0.58

 Fres

-0.58

 Brun

-0.55

 Vaugh

-0.55

POSITIVE LOGITS

 shit

0.93

 THEIR

0.86

 oppression

0.85

 oppressed

0.82

 agendas

0.82

 mankind

0.80

 injustice

0.80

 humanity

0.79

 behalf

0.79

 civilization

0.78

Activations Density 0.420%

phrases related to government actions and responsibilities

No Comments

No Known Activations