INDEX

Explanations

phrases related to personal experiences and reflections

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_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CVE

-0.54

 goto

-0.53

ãĥ¼ãĥĨ

-0.52

 Reef

-0.51

lbs

-0.50

 Franks

-0.50

 Constantin

-0.49

etc

-0.49

 mans

-0.49

 echoed

-0.49

POSITIVE LOGITS

jriwal

0.81

anmar

0.80

[/

0.79

estine

0.79

vernment

0.74

odore

0.73

usterity

0.73

rimination

0.72

withstanding

0.72

mosp

0.72

Activations Density 0.245%

phrases related to personal experiences and reflections

No Comments

No Known Activations