INDEX

Explanations

references to recent events and statements made in public forums

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

/-

-0.80

)/

-0.72

agogue

-0.69

oyal

-0.68

enfranch

-0.68

orno

-0.68

illusion

-0.66

hov

-0.64

ovan

-0.63

ibaba

-0.63

POSITIVE LOGITS

 remarks

1.03

 tweets

0.97

 tweeted

0.93

 stating

0.91

 remark

0.89

 comments

0.88

 sarcast

0.87

 tweeting

0.86

 tweet

0.86

 quotes

0.85

Activations Density 0.296%

references to recent events and statements made in public forums

No Comments

No Known Activations