INDEX

Explanations

words related to medical conditions and treatments, including tuberculosis, infection, pathogens, and screening

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

icals

-0.86

etheless

-0.85

nesday

-0.72

osponsors

-0.71

oran

-0.71

padding

-0.70

ascus

-0.70

dies

-0.69

rast

-0.67

anguage

-0.67

POSITIVE LOGITS

ppe

0.97

Ã±o

0.91

 versa

0.87

lda

0.77

olate

0.75

Film

0.73

gow

0.72

0.71

ller

0.70

vic

0.70

Activations Density 0.043%

words related to medical conditions and treatments, including tuberculosis, infection, pathogens, and screening

No Comments

No Known Activations