INDEX

Explanations

concepts related to political, economic, sociological, and historical analysis

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

upon

-0.77

ocate

-0.70

ritch

-0.65

ties

-0.64

atron

-0.63

Ì¶

-0.61

lance

-0.61

ibraries

-0.61

brace

-0.60

thood

-0.59

POSITIVE LOGITS

 occasions

1.51

 basis

1.46

 behalf

1.39

 occasion

1.35

 doorstep

1.20

 grounds

1.17

eve

1.08

 pretext

1.05

 verge

1.04

 heels

1.03

Activations Density 1.283%

concepts related to political, economic, sociological, and historical analysis

No Comments

No Known Activations