INDEX

Explanations

ingredients in recipes

oai_token-act-pair · gpt-3.5-turbo

indicators of recipes or cooking instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 someday

-0.85

 interoper

-0.78

 debugger

-0.69

reon

-0.69

 patrols

-0.68

 diagn

-0.65

 exhibitions

-0.63

 checkpoints

-0.63

 alerts

-0.62

 glimps

-0.62

POSITIVE LOGITS

Ingredients

1.40

redients

1.25

 ingredients

1.12

 Ingredients

1.12

 almonds

0.95

Â½

0.94

 oats

0.92

 yeast

0.90

 parchment

0.87

 herbs

0.83

Activations Density 0.148%

ingredients in recipes

indicators of recipes or cooking instructions

No Comments

No Known Activations