INDEX

Explanations

mention of firearms, law enforcement, legal actions, injuries, and court cases

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

 swearing

-0.66

 Lara

-0.57

 Cutter

-0.57

£ı

-0.57

 tender

-0.55

 recognition

-0.54

 Tate

-0.54

 Lauder

-0.54

Fas

-0.54

actionDate

-0.54

POSITIVE LOGITS

Â½

1.26

th

1.13

1.12

1.11

1.09

1.08

1.07

1.06

Activations Density 0.752%

mention of firearms, law enforcement, legal actions, injuries, and court cases

No Comments

No Known Activations