INDEX

Explanations

references to time spans, particularly those related to recent years and changes over time

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

inki

-0.77

Fine

-0.71

cause

-0.66

Tickets

-0.65

oops

-0.64

agra

-0.63

BUT

-0.62

Done

-0.62

aith

-0.61

AB

-0.61

POSITIVE LOGITS

 there

0.81

we

0.80

 studies

0.71

idents

0.70

 however

0.69

 meanwhile

0.69

 psychologists

0.67

 successive

0.66

 moreover

0.66

 astronomers

0.64

Activations Density 0.102%

references to time spans, particularly those related to recent years and changes over time

No Comments

No Known Activations