INDEX

Explanations

mentions of "laps" or "lapse" indicating a recurring theme of memory or performance incidents

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

hood

-0.66

ISON

-0.65

 CARD

-0.64

 brunt

-0.61

 plurality

-0.60

 abund

-0.58

pole

-0.57

 tenant

-0.57

BI

-0.57

 IMAGES

-0.56

POSITIVE LOGITS

es

1.08

alos

0.86

alm

0.86

ed

0.85

luster

0.83

ippi

0.82

esian

0.82

ioned

0.81

itant

0.79

ieve

0.79

Activations Density 0.005%

mentions of "laps" or "lapse" indicating a recurring theme of memory or performance incidents

No Comments

No Known Activations

mentions of "laps" or "lapse" indicating a recurring theme of memory or performance incidents

No Comments

No Known Activations