INDEX

Explanations

terms related to dietary restrictions, specifically gluten and dairy allergies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs49152-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

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

CLASSIFIED

-0.84

 Phant

-0.73

ILA

-0.69

HCR

-0.69

 Ones

-0.67

 Warrant

-0.66

pload

-0.66

 Hawth

-0.65

hare

-0.65

jun

-0.65

POSITIVE LOGITS

 intolerance

0.98

 gluten

0.95

 intoler

0.91

 allergy

0.89

iness

0.88

 sensitivity

0.84

 allergies

0.84

less

0.84

 tolerant

0.81

bite

0.81

Activations Density 0.007%

terms related to dietary restrictions, specifically gluten and dairy allergies

No Comments

No Known Activations