INDEX

Explanations

mentions of particular individuals or characters associated with specific traits or roles

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

iculty

-0.78

LCS

-0.73

AMY

-0.68

 Compass

-0.68

reek

-0.67

REE

-0.65

riter

-0.64

 Commonwealth

-0.64

 Monstrous

-0.64

IRD

-0.62

POSITIVE LOGITS

aldo

0.96

atis

0.93

lich

0.88

ich

0.88

ci

0.87

zon

0.87

vana

0.85

Rin

0.85

zai

0.84

zeb

0.84

Activations Density 0.005%

mentions of particular individuals or characters associated with specific traits or roles

No Comments

No Known Activations