INDEX

Explanations

mentions and references to specific names and topics in written content, likely from social media or news articles

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

 cumbers

-0.80

 outsiders

-0.70

 embargo

-0.69

 exha

-0.68

 breadth

-0.68

 salient

-0.68

 passage

-0.67

 carbohyd

-0.67

 bree

-0.66

 increment

-0.66

POSITIVE LOGITS

_-_

1.30

1.28

_(

1.22

_.

1.21

__

1.20

1.18

Jr

1.14

()

1.08

/,

0.99

Stud

0.99

Activations Density 0.907%

mentions and references to specific names and topics in written content, likely from social media or news articles

No Comments

No Known Activations