INDEX

Explanations

medical terms related to diseases, pathogens, or diagnostic methods

oai_token-act-pair · gpt-3.5-turbo

references to paths or pathways in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 sterling

-0.70

zona

-0.65

Mub

-0.63

 contrace

-0.62

CHAR

-0.62

 Lange

-0.61

ileged

-0.59

 disadvant

-0.59

 Marketable

-0.59

Luc

-0.59

POSITIVE LOGITS

finding

1.51

finder

1.29

ologies

1.23

ogen

1.18

find

1.14

ways

1.14

ologist

1.05

ophys

0.98

ogenesis

0.94

ozo

0.92

Activations Density 0.040%

medical terms related to diseases, pathogens, or diagnostic methods

references to paths or pathways in various contexts

No Comments

No Known Activations