INDEX

Explanations

locations or places

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eries

-0.69

vernment

-0.68

ggles

-0.64

ework

-0.63

alty

-0.62

affle

-0.59

icide

-0.59

ovi

-0.59

ãĤ¡

-0.58

ocious

-0.57

POSITIVE LOGITS

 atop

1.16

 somewhere

0.98

 inside

0.96

 indoors

0.93

 near

0.90

 beside

0.89

 elsewhere

0.89

 therein

0.87

 outdoors

0.86

 Somewhere

0.86

Activations Density 1.430%

locations or places

No Comments

No Known Activations