INDEX

Explanations

themes related to self-examination and personal accountability

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

boa

-0.68

ossal

-0.68

vae

-0.68

ãĤ©

-0.66

Kov

-0.64

UNCH

-0.62

quickShipAvailable

-0.61

ENG

-0.60

Mech

-0.60

ateur

-0.60

POSITIVE LOGITS

 selves

1.10

cale

1.02

cape

0.93

heet

0.88

etting

0.87

pring

0.87

omething

0.86

creen

0.80

ervative

0.79

linger

0.79

Activations Density 0.101%

themes related to self-examination and personal accountability

No Comments

No Known Activations