INDEX

Explanations

mentions of specific entities or organizations, particularly related to campaigns, sanctions, and incidents

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

ention

-0.71

ications

-0.63

imity

-0.60

igslist

-0.60

ded

-0.57

ijing

-0.57

ively

-0.57

amina

-0.56

cess

-0.56

icy

-0.56

POSITIVE LOGITS

vernment

1.12

raphic

0.91

reens

0.90

iants

0.86

roups

0.85

reetings

0.79

hetto

0.78

irlfriend

0.76

wyn

0.75

ORGE

0.75

Activations Density 1.130%

mentions of specific entities or organizations, particularly related to campaigns, sanctions, and incidents

No Comments

No Known Activations