INDEX

Explanations

phrases associated with online communities or digital platforms

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

enegger

-0.92

heit

-0.92

enhagen

-0.82

iland

-0.75

ebus

-0.70

gling

-0.70

bler

-0.69

swick

-0.65

owship

-0.64

abee

-0.64

POSITIVE LOGITS

PIN

0.65

Effects

0.65

Medium

0.63

sharp

0.63

©¶æ

0.62

å§

0.62

atar

0.61

 Noir

0.60

 Sakuya

0.58

credit

0.58

Activations Density 0.160%

phrases associated with online communities or digital platforms

No Comments

No Known Activations