INDEX

Explanations

newsworthy events and information, particularly press releases and social media uproars

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iencies

-0.76

ahime

-0.73

 chimpanzees

-0.71

 subsistence

-0.69

 Flavoring

-0.68

 environments

-0.67

 mobility

-0.67

 sacrific

-0.64

 biologically

-0.64

 mutants

-0.64

POSITIVE LOGITS

 circulated

1.14

 titled

1.08

 excerpts

1.06

 outlining

1.05

 Pastebin

1.04

 redacted

1.04

 summar

1.02

 reprinted

1.01

ebin

0.96

 informing

0.96

Activations Density 5.967%

newsworthy events and information, particularly press releases and social media uproars

No Comments

No Known Activations