INDEX

Explanations

references to cars or automotive content

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

iciency

-0.70

ãĥĥãĥĪ

-0.70

ereo

-0.69

 Falls

-0.69

imity

-0.69

hower

-0.67

 Murdoch

-0.67

EngineDebug

-0.66

ures

-0.64

urer

-0.64

POSITIVE LOGITS

STON

1.14

olina

1.08

SON

1.05

LOS

1.04

PET

1.04

MEN

0.96

LIN

0.92

RY

0.91

INA

0.88

BACK

0.88

Activations Density 0.002%

references to cars or automotive content

No Comments

No Known Activations