INDEX

Explanations

references to the National Health Service (NHS)

oai_token-act-pair · gpt-3.5-turbo

mentions of the NHS (National Health Service)

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

gered

-0.88

secut

-0.78

nings

-0.76

estamp

-0.73

nesota

-0.72

oths

-0.70

ographed

-0.67

wagon

-0.67

tha

-0.66

stad

-0.65

POSITIVE LOGITS

NHS

0.87

 healthcare

0.85

aceutical

0.85

 privat

0.79

earch

0.78

 hospitals

0.76

 nursing

0.76

 workforce

0.75

 Improvement

0.73

HS

0.73

Activations Density 0.010%

references to the National Health Service (NHS)

mentions of the NHS (National Health Service)

No Comments

No Known Activations