INDEX

Explanations

information related to news articles or reports

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

username

-0.65

opter

-0.58

uds

-0.58

ttp

-0.56

orr

-0.54

 Stall

-0.54

ilaterally

-0.54

tons

-0.53

href

-0.53

zos

-0.53

POSITIVE LOGITS

 CITY

0.95

WASHINGTON

0.89

SHARE

0.80

VILLE

0.79

 COUNTY

0.79

LIN

0.75

JUL

0.74

MEN

0.73

MEN

0.73

SPR

0.72

Activations Density 0.722%

information related to news articles or reports

No Comments

No Known Activations