INDEX

Explanations

negations and their implications within a broader context

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

 successors

-0.69

 Cosponsors

-0.68

artney

-0.68

OULD

-0.67

vernment

-0.66

ebted

-0.65

ipel

-0.65

enda

-0.62

 subsequent

-0.62

ortment

-0.61

POSITIVE LOGITS

 understatement

0.84

 scarce

0.81

 bitch

0.74

 finite

0.71

 noun

0.70

 commodity

0.69

---------

0.69

 causation

0.69

 healer

0.68

 lubric

0.68

Activations Density 0.235%

negations and their implications within a broader context

No Comments

No Known Activations