INDEX

Explanations

references to political events and statements

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

 beforehand

-0.80

 initially

-0.77

 originally

-0.64

amba

-0.60

 blah

-0.60

 otherwise

-0.59

 preceding

-0.58

 Originally

-0.58

 previously

-0.58

bell

-0.57

POSITIVE LOGITS

here

0.77

 anew

0.72

Ô

0.71

aukee

0.70

CLUS

0.69

IRE

0.67

adays

0.65

nir

0.65

 resur

0.65

YA

0.65

Activations Density 0.355%

references to political events and statements

No Comments

No Known Activations