INDEX

Explanations

mentions of hormones and medical terms related to physical conditions

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

Pont

-0.80

à¦

-0.80

pee

-0.71

kay

-0.68

irrel

-0.67

gone

-0.66

PokÃ©

-0.65

Holy

-0.64

peg

-0.64

illions

-0.63

POSITIVE LOGITS

 bluntly

0.85

 sarcast

0.79

:"

0.79

 afterward

0.78

 anecd

0.77

 goodbye

0.75

 afterwards

0.74

he

0.71

 yesterday

0.71

 Thursday

0.69

Activations Density 1.262%

mentions of hormones and medical terms related to physical conditions

No Comments

No Known Activations