INDEX

Explanations

phrases related to medical treatments and diagnoses

oai_token-act-pair · gpt-3.5-turbo

phrases and terms related to medical procedures and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 submer

-0.92

glomer

-0.86

 submar

-0.83

 Alban

-0.82

Bom

-0.79

Aeg

-0.78

 Albania

-0.78

olith

-0.76

 Dupl

-0.76

DN

-0.75

POSITIVE LOGITS

Hay

2.70

Hay

2.37

 Hayes

2.13

 Hayden

1.92

 Hayward

1.63

hay

1.63

 Garland

1.14

bay

1.13

 Harrison

1.07

 Hastings

1.03

Activations Density 0.231%

phrases related to medical treatments and diagnoses

phrases and terms related to medical procedures and conditions

No Comments

No Known Activations