INDEX

Explanations

terms related to urban and rural areas

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

cius

-0.76

ãĤ´ãĥ³

-0.75

nir

-0.74

uter

-0.74

iris

-0.72

qt

-0.72

INS

-0.72

wright

-0.72

othal

-0.71

isters

-0.70

POSITIVE LOGITS

 dwell

1.03

ization

0.99

ized

0.89

 areas

0.88

 landscapes

0.87

izing

0.85

 environments

0.85

isation

0.83

 dwelling

0.82

icity

0.81

Activations Density 0.974%

terms related to urban and rural areas

No Comments

No Known Activations