INDEX

Explanations

data points that belong to specific categories or are part of a series

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

cies

-0.77

zzle

-0.74

CPC

-0.70

imity

-0.70

ãĥĢ

-0.69

ãĥĥ

-0.67

ãĥĦ

-0.66

tery

-0.65

 disarm

-0.64

ku

-0.64

POSITIVE LOGITS

OTUS

1.39

ORE

1.20

RIPT

1.19

IENCE

1.18

OTT

1.13

REAM

1.09

RIP

1.05

ADA

1.02

OTS

1.00

RAM

0.98

Activations Density 0.015%

data points that belong to specific categories or are part of a series

No Comments

No Known Activations