INDEX

Explanations

phrases related to proteins

oai_token-act-pair · gpt-3.5-turbo

references to protein and its various forms or effects

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.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

 Lauder

-0.80

uation

-0.78

rius

-0.76

uate

-0.75

igators

-0.74

tainment

-0.73

uating

-0.73

pole

-0.69

quished

-0.69

REAM

-0.68

POSITIVE LOGITS

 isolate

0.83

 powd

0.72

protein

0.71

hedral

0.71

aceous

0.70

asms

0.68

 concentrate

0.68

sil

0.67

 powder

0.66

Ô

0.66

Activations Density 0.080%

phrases related to proteins

references to protein and its various forms or effects

No Comments

No Known Activations