INDEX

Explanations

phrases related to sending messages or communication

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

ords

-0.76

endars

-0.74

ternity

-0.70

enne

-0.68

umbers

-0.68

umbered

-0.65

everal

-0.65

erenn

-0.65

itates

-0.65

lege

-0.65

POSITIVE LOGITS

 message

1.10

 conveyed

1.00

 messages

0.96

 reson

0.88

 preached

0.85

message

0.85

 loud

0.81

 communicated

0.81

 Messages

0.81

 resonate

0.81

Activations Density 0.055%

phrases related to sending messages or communication

No Comments

No Known Activations