INDEX

Explanations

paths or directories in a programming 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_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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Archdemon

-0.72

 Samar

-0.62

ï¸ı

-0.60

Flor

-0.60

 Cobb

-0.59

ooth

-0.59

orem

-0.58

onement

-0.58

istle

-0.58

Bey

-0.56

POSITIVE LOGITS

local

0.99

share

0.98

bin

0.83

ctic

0.75

include

0.74

src

0.73

fecture

0.71

paid

0.67

¨

0.67

lib

0.66

Activations Density 0.019%

paths or directories in a programming context

No Comments

No Known Activations