INDEX

Explanations

geographical locations and identifiers related to conflict zones

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

 Grateful

-0.68

 crank

-0.67

sych

-0.67

Knight

-0.64

MPH

-0.64

ãĤ´ãĥ³

-0.64

Roberts

-0.64

 Logged

-0.63

 Weaver

-0.63

rawdownloadcloneembedreportprint

-0.63

POSITIVE LOGITS

ascus

0.99

ilan

0.92

awi

0.90

etsk

0.90

ussia

0.86

assies

0.85

uala

0.83

akh

0.83

 unpop

0.82

abul

0.82

Activations Density 0.101%

geographical locations and identifiers related to conflict zones

No Comments

No Known Activations