INDEX

Explanations

the name "Cameron" in various contexts, such as politics, sports, and personal interactions

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

irements

-0.84

hips

-0.75

omething

-0.72

ĻĤ

-0.71

ebin

-0.71

ahead

-0.69

uably

-0.69

liness

-0.69

Ñĭ

-0.67

ĪĴ

-0.67

POSITIVE LOGITS

 Cameron

0.86

 Slater

0.80

 Diaz

0.79

 Pearce

0.75

ameron

0.72

 Miliband

0.69

 Downing

0.69

 Osborne

0.68

 Palace

0.68

Ack

0.68

Activations Density 0.026%

the name "Cameron" in various contexts, such as politics, sports, and personal interactions

No Comments

No Known Activations