INDEX

Explanations

details about people being taken to hospitals or medical facilities

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

natureconservancy

-0.77

 minded

-0.67

 fielded

-0.66

 amassed

-0.64

 innate

-0.63

 inherited

-0.63

 incumbent

-0.62

 horizont

-0.62

 ambition

-0.62

reci

-0.61

POSITIVE LOGITS

 hospital

0.84

ospital

0.81

ilet

0.79

ombs

0.78

 Bellev

0.77

ADRA

0.77

Ô

0.77

 Guantanamo

0.77

ichita

0.76

ACTED

0.73

Activations Density 0.139%

details about people being taken to hospitals or medical facilities

No Comments

No Known Activations