INDEX

Explanations

information related to historical events, political controversies, and cultural references

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

 Dragonbound

-0.72

ogy

-0.70

 Opportun

-0.69

antha

-0.65

hower

-0.63

 gorilla

-0.61

Syl

-0.60

ãĥ¼ãĥĨ

-0.59

achus

-0.58

ipation

-0.58

POSITIVE LOGITS

1.06

1.03

1.02

1.01

0.99

Activations Density 0.336%

information related to historical events, political controversies, and cultural references

No Comments

No Known Activations