INDEX

Explanations

phrases or words related to food consumption

oai_token-act-pair · gpt-3.5-turbo

references to the action of eating

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

 Gemini

-0.75

 Stellar

-0.75

channelAvailability

-0.72

worthiness

-0.72

Aus

-0.69

 Stra

-0.66

 Constable

-0.65

 Nich

-0.64

 Lash

-0.64

PV

-0.64

POSITIVE LOGITS

 habits

1.02

 eaten

1.00

 foods

0.97

eteria

0.96

 meals

0.95

eat

0.95

 breakfast

0.94

anut

0.85

 lunch

0.85

 nutrit

0.85

Activations Density 0.029%

phrases or words related to food consumption

references to the action of eating

No Comments

No Known Activations