INDEX

Explanations

words related to ailments or medical conditions

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "ent" or "entitlement"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Mub

-0.72

 pine

-0.65

BMC

-0.63

 Bows

-0.62

 dwind

-0.61

 bumped

-0.61

 gauge

-0.61

 hammered

-0.61

 pigs

-0.58

 burned

-0.58

POSITIVE LOGITS

ent

4.33

ents

2.66

enting

2.53

ENT

2.52

ency

2.12

ented

2.11

enter

2.09

ental

2.02

ento

2.02

ente

2.01

Activations Density 0.022%

words related to ailments or medical conditions

words related to the concept of "ent" or "entitlement"

No Comments

No Known Activations