INDEX

Explanations

names or locations related to the word "Ram"

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_fs6144-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_6144

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

6,144

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

RAFT

-0.68

ternity

-0.66

URR

-0.65

XT

-0.62

 predic

-0.62

 Carib

-0.58

LECT

-0.57

 Morales

-0.57

 Spit

-0.57

chnology

-0.56

POSITIVE LOGITS

irez

1.34

ming

1.20

pling

1.17

blers

1.17

pton

1.16

pled

1.07

mers

1.02

bling

0.99

bler

0.99

adan

0.98

Activations Density 0.289%

names or locations related to the word "Ram"

No Comments

No Known Activations