INDEX

Explanations

references to geographical 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

éĹĺ

-0.78

atron

-0.72

ILLE

-0.71

bian

-0.68

Priv

-0.65

itarian

-0.65

ipop

-0.65

Fas

-0.65

nder

-0.64

ilyn

-0.63

POSITIVE LOGITS

fields

0.90

field

0.86

plane

0.84

grass

0.83

sheet

0.82

spring

0.80

side

0.78

keepers

0.77

keeping

0.77

planes

0.76

Activations Density 0.465%

references to geographical locations or places

No Comments

No Known Activations