INDEX

Explanations

code snippets related to variable aggregation and mathematical operations

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

SPONSORED

-0.85

mercial

-0.80

iversal

-0.75

liv

-0.72

conom

-0.72

ivia

-0.72

luster

-0.71

itant

-0.70

ngth

-0.69

imony

-0.69

POSITIVE LOGITS

[];

1.16

{}

1.04

nil

0.99

 NULL

0.98

 null

0.94

 False

0.89

========

0.88

============

0.87

[]

0.87

0.84

Activations Density 0.014%

code snippets related to variable aggregation and mathematical operations

No Comments

No Known Activations