INDEX

Explanations

phrases indicating a requirement or necessity

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

Ń·

-0.63

Zam

-0.59

creen

-0.59

 Democr

-0.59

 Dism

-0.58

ihu

-0.58

azar

-0.57

 Pill

-0.56

 Rost

-0.56

zees

-0.56

POSITIVE LOGITS

lessly

1.29

 urgently

0.82

 attention

0.81

0.77

 patience

0.77

 assistance

0.74

 reinforcements

0.73

 reminding

0.72

 urgent

0.72

lest

0.71

Activations Density 1.084%

phrases indicating a requirement or necessity

No Comments

No Known Activations