INDEX

Explanations

medical terms and specific measurements

oai_token-act-pair · gpt-3.5-turbo

terms related to biology and health

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

 Buch

-0.66

falls

-0.62

Bra

-0.61

 Machina

-0.61

SPR

-0.61

 Mich

-0.61

ALT

-0.61

 Chun

-0.60

ORN

-0.59

bread

-0.58

POSITIVE LOGITS

ierre

0.79

agascar

0.77

etheless

0.76

phrine

0.69

terday

0.67

ãĤ´ãĥ³

0.64

unia

0.64

jriwal

0.64

 Affairs

0.64

 Confederation

0.64

Activations Density 0.257%

medical terms and specific measurements

terms related to biology and health

No Comments

No Known Activations