INDEX

Explanations

instances of the word "opposite" and its related forms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

beans

-0.80

uay

-0.77

ulic

-0.76

 Annotations

-0.74

anwhile

-0.73

lished

-0.71

ule

-0.71

urrent

-0.71

uzz

-0.70

atche

-0.70

POSITIVE LOGITS

 side

0.89

 sexes

0.86

 sides

0.85

 extremes

0.84

osite

0.83

 direction

0.77

 opposite

0.77

sex

0.75

 scenario

0.74

 gender

0.73

Activations Density 0.024%

instances of the word "opposite" and its related forms

No Comments

No Known Activations