INDEX

Explanations

possessive forms indicating ownership or attributes

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

»

-0.80

lehem

-0.79

Õ

-0.79

Ú

-0.77

ENN

-0.76

Balt

-0.75

ÙĲ

-0.74

cible

-0.73

Ïī

-0.72

BT

-0.72

POSITIVE LOGITS

 biggest

1.03

 penchant

0.99

 inability

0.99

 detractors

0.97

 spokesman

0.95

 obsession

0.93

 newest

0.92

 refusal

0.91

 motives

0.91

 actions

0.90

Activations Density 0.130%

possessive forms indicating ownership or attributes

No Comments

No Known Activations