INDEX

Explanations

verbs related to fulfilling or fulfilling actions

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

oss

-0.72

weed

-0.67

ARC

-0.66

opers

-0.65

Downloadha

-0.64

 prone

-0.61

 spray

-0.61

otin

-0.59

oxin

-0.59

bestos

-0.58

POSITIVE LOGITS

 fulfilled

1.08

 fulfil

0.99

ment

0.97

ments

0.94

 fulf

0.93

 Satisf

0.88

 fulfillment

0.86

 obligations

0.85

actory

0.84

 fulfill

0.84

Activations Density 0.036%

verbs related to fulfilling or fulfilling actions

No Comments

No Known Activations