INDEX

Explanations

medical symptoms and conditions related to skin irritations, inflammation, and allergic reactions

oai_token-act-pair · gpt-3.5-turbo

terms related to symptoms and medical conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rolet

-0.88

soDeliveryDate

-0.82

winner

-0.70

zees

-0.69

 commons

-0.68

ettel

-0.68

ãĤ¨ãĥ«

-0.68

Rules

-0.66

Calif

-0.65

 Tycoon

-0.64

POSITIVE LOGITS

 symptoms

1.19

 inflammation

1.13

 Symptoms

1.12

 syndrome

1.00

 symptom

1.00

 Syndrome

0.97

 lymph

0.94

 sensation

0.93

 swelling

0.92

 vascular

0.89

Activations Density 0.310%

medical symptoms and conditions related to skin irritations, inflammation, and allergic reactions

terms related to symptoms and medical conditions

No Comments

No Known Activations