INDEX

Explanations

variations of the word "or" indicating alternatives or choices

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

HER

-0.88

ords

-0.78

ETS

-0.77

ocracy

-0.73

plates

-0.72

onomy

-0.72

 Tycoon

-0.72

 Pony

-0.72

arte

-0.69

ocrats

-0.69

POSITIVE LOGITS

 misplaced

1.16

 inadequ

1.09

 unwanted

1.05

chard

1.04

 defective

1.03

 malfunction

1.02

 inacc

1.02

 misunderstood

1.00

 worse

1.00

 inaccur

0.99

Activations Density 0.070%

variations of the word "or" indicating alternatives or choices

No Comments

No Known Activations