INDEX

Explanations

occurrences of the word "the."

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

ufact

-0.86

isSpecialOrderable

-0.76

staking

-0.75

âĵĺ

-0.71

eson

-0.70

teness

-0.69

ruary

-0.68

elaide

-0.67

rency

-0.67

terness

-0.65

POSITIVE LOGITS

 Kardash

0.92

 Difference

0.83

 Latest

0.71

 Twins

0.71

 Nation

0.71

 Networks

0.69

oret

0.69

 Facts

0.67

 Forces

0.67

 Sounds

0.66

Activations Density 0.012%

occurrences of the word "the."

No Comments

No Known Activations