INDEX

Explanations

comparisons between different entities or concepts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

eds

-0.75

Bern

-0.66

icken

-0.64

engine

-0.62

bags

-0.59

planes

-0.59

ione

-0.59

arma

-0.58

ircraft

-0.57

hiba

-0.56

POSITIVE LOGITS

 anything

0.77

 usual

0.76

acles

0.74

 anticipated

0.69

 rewriting

0.67

ascript

0.67

 worrying

0.67

EStreamFrame

0.67

 curing

0.66

kill

0.65

Activations Density 0.116%

comparisons between different entities or concepts

No Comments

No Known Activations