INDEX

Explanations

words related to medical conditions and treatments

oai_token-act-pair · gpt-3.5-turbo

references to diseases, medical conditions, and related treatments or substances

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

redit

-0.80

ortunately

-0.78

ront

-0.78

redo

-0.77

natureconservancy

-0.77

rue

-0.74

erate

-0.73

ouf

-0.72

arse

-0.71

ophys

-0.70

POSITIVE LOGITS

 polio

0.85

 vaccination

0.84

 measles

0.82

pox

0.75

 Â®

0.73

 vaccinations

0.73

 vaccine

0.68

 vaccines

0.67

 mushrooms

0.66

 scratch

0.66

Activations Density 0.047%

words related to medical conditions and treatments

references to diseases, medical conditions, and related treatments or substances

No Comments

No Known Activations