INDEX

Explanations

numerical values formatted as text in a structured presentation, such as references or lists in a document

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

 millenn

-0.86

anooga

-0.78

querque

-0.73

ionics

-0.68

 contests

-0.67

 passionate

-0.66

 masc

-0.66

 tragedies

-0.66

 histories

-0.65

 mutual

-0.65

POSITIVE LOGITS

1.17

1.14

1.13

1.12

1.11

1.10

Activations Density 0.378%

numerical values formatted as text in a structured presentation, such as references or lists in a document

No Comments

No Known Activations