INDEX

Explanations

words related to internal organs, specifically the brain and heart

oai_token-act-pair · gpt-3.5-turbo

references to the brain and emotional connections, particularly involving hearts and minds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ression

-0.70

ressive

-0.67

ALLY

-0.67

Recomm

-0.66

Delivery

-0.66

BUG

-0.63

rip

-0.62

onomy

-0.59

 Apocalypse

-0.58

Definition

-0.56

POSITIVE LOGITS

paces

1.51

chool

1.44

mith

1.43

pace

1.42

pring

1.42

creen

1.40

hips

1.31

hare

1.23

peed

1.23

cale

1.23

Activations Density 0.184%

words related to internal organs, specifically the brain and heart

references to the brain and emotional connections, particularly involving hearts and minds

No Comments

No Known Activations