INDEX

Explanations

programming-related content, specifically discussing concepts like mapping, data representation, and data structures

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

etheless

-0.73

uitous

-0.72

ifications

-0.71

IFIED

-0.68

nets

-0.67

ashtra

-0.66

 GOODMAN

-0.66

ERAL

-0.65

orage

-0.64

icipated

-0.63

POSITIVE LOGITS

ller

1.27

ppo

1.26

llers

1.25

eling

1.25

ck

1.20

eping

1.20

gging

1.19

lder

1.17

lling

1.17

cker

1.17

Activations Density 0.660%

programming-related content, specifically discussing concepts like mapping, data representation, and data structures

No Comments

No Known Activations