INDEX

Explanations

names or titles given to specific systems, projects, or groups

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

SPONSORED

-0.82

 baseman

-0.72

Constructed

-0.71

 horr

-0.63

 reassure

-0.62

 horrified

-0.62

 enjoyed

-0.62

 dstg

-0.61

Edited

-0.61

 tempted

-0.61

POSITIVE LOGITS

"#

0.93

0.89

0.80

COP

0.80

 Operation

0.79

``

0.78

 Fancy

0.73

 Excellence

0.71

RED

0.70

Activations Density 0.868%

names or titles given to specific systems, projects, or groups

No Comments

No Known Activations