INDEX

Explanations

phrases related to conversations and interactions between individuals, especially reflecting on experiences and sharing insights

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

ãĤ´ãĥ³

-0.76

 Â®

-0.66

hered

-0.65

zu

-0.63

ãĥĭ

-0.62

apor

-0.61

antine

-0.61

expr

-0.59

arthed

-0.58

!:

-0.58

POSITIVE LOGITS

 blah

1.21

 stuff

1.12

 everybody

1.10

romeda

1.07

 yeah

1.02

 hopefully

1.00

 maybe

0.99

 frankly

0.94

 secondly

0.93

 somebody

0.90

Activations Density 0.251%

phrases related to conversations and interactions between individuals, especially reflecting on experiences and sharing insights

No Comments

No Known Activations