INDEX

Explanations

phrases related to current events and news topics

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

 Instr

-0.83

assies

-0.64

 lest

-0.64

SPONSORED

-0.62

 explan

-0.59

 undermin

-0.58

Oo

-0.58

ecause

-0.57

ÃŃa

-0.57

avorite

-0.57

POSITIVE LOGITS

/-

0.76

\":

0.75

!--

0.71

PDATED

0.69

)/

0.69

)-

0.67

ãĢĳ

0.65

mosp

0.61

)*

0.61

lihood

0.60

Activations Density 0.087%

phrases related to current events and news topics

No Comments

No Known Activations