INDEX

Explanations

mentions of hunger

oai_token-act-pair · gpt-3.5-turbo

references to hunger or being hungry

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

idine

-0.86

 CLSID

-0.81

Downloadha

-0.78

ioxide

-0.71

perty

-0.69

 Offic

-0.68

BuyableInstoreAndOnline

-0.68

 patented

-0.67

DCS

-0.67

istically

-0.66

POSITIVE LOGITS

 hungry

0.97

 meals

0.96

 ghosts

0.90

ness

0.87

 Hungry

0.81

 thirsty

0.78

 starving

0.77

iesta

0.75

 crocod

0.73

ening

0.73

Activations Density 0.016%

mentions of hunger

references to hunger or being hungry

No Comments

No Known Activations