INDEX

Explanations

medical or anatomical terms, particularly related to fractures and body parts, focusing especially on the femur

oai_token-act-pair · gpt-3.5-turbo

terms related to femininity or female attributes

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

 Shinra

-0.71

 Oaks

-0.68

 Carbuncle

-0.67

 Yose

-0.66

 guiActiveUnfocused

-0.65

BuyableInstoreAndOnline

-0.64

ively

-0.63

 Monarch

-0.62

 Amen

-0.62

 Bentley

-0.61

POSITIVE LOGITS

puter

0.98

rite

0.94

inity

0.93

ldom

0.91

ili

0.87

ilit

0.87

orp

0.85

uer

0.84

bots

0.82

pire

0.82

Activations Density 0.031%

medical or anatomical terms, particularly related to fractures and body parts, focusing especially on the femur

terms related to femininity or female attributes

No Comments

No Known Activations