INDEX

Explanations

specific patterns related to coding or formatting, possibly related to a particular website or platform

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

 UNITED

-0.56

 pione

-0.50

 earthqu

-0.50

 Coat

-0.48

 entreprene

-0.47

 notor

-0.47

compan

-0.47

 sqor

-0.46

redo

-0.44

roximately

-0.44

POSITIVE LOGITS

1.65

-)

1.30

âĢĳ

1.23

-'

1.23

-.

1.14

-[

1.14

-$

1.13

-(

1.11

%-

1.09

Activations Density 1.090%

specific patterns related to coding or formatting, possibly related to a particular website or platform

No Comments

No Known Activations