INDEX

Explanations

medical and technical terms or phrases

oai_token-act-pair · gpt-3.5-turbo

phrases related to medical awareness and the consequences of actions

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

 Quentin

-0.76

 Miko

-0.65

 Zeit

-0.63

 Metatron

-0.59

 Fool

-0.58

 pend

-0.57

 stal

-0.57

Pak

-0.57

Tot

-0.56

 Strong

-0.55

POSITIVE LOGITS

itud

0.80

abouts

0.77

ãĥ¼ãĤ¯

0.76

itudes

0.69

ELL

0.68

burgh

0.64

 accompl

0.64

ãĤ´ãĥ³

0.63

iana

0.63

borgh

0.62

Activations Density 0.858%

medical and technical terms or phrases

phrases related to medical awareness and the consequences of actions

No Comments

No Known Activations