INDEX

Explanations

names of individuals and locations, especially related to law enforcement and political figures

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

terday

-0.89

ifully

-0.80

theless

-0.79

 wise

-0.75

etheless

-0.73

 profiling

-0.71

 sanity

-0.70

 parity

-0.70

 compe

-0.69

 karma

-0.68

POSITIVE LOGITS

onian

1.07

osphere

0.93

ospels

0.90

 Hotel

0.89

venth

0.88

 Mountains

0.83

iest

0.83

ocene

0.83

 Museum

0.82

 River

0.81

Activations Density 1.666%

names of individuals and locations, especially related to law enforcement and political figures

No Comments

No Known Activations