INDEX

Explanations

names and titles in a sports context

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

yip

-0.85

imeters

-0.65

achev

-0.64

avorite

-0.61

uity

-0.58

lid

-0.57

ragon

-0.56

agascar

-0.55

aucus

-0.54

uously

-0.54

POSITIVE LOGITS

 Whedon

0.77

 Marriott

0.76

ernaut

0.73

neys

0.73

ournal

0.72

 Rowling

0.69

Cole

0.68

iard

0.68

EStream

0.67

strap

0.67

Activations Density 1.283%

names and titles in a sports context

No Comments

No Known Activations