INDEX

Explanations

adaptations of recipes

oai_token-act-pair · gpt-3.5-turbo

mentions of recipes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

lasses

-0.85

phe

-0.74

osc

-0.72

usters

-0.71

 Stra

-0.71

etime

-0.71

gow

-0.70

ãĥĥãĥī

-0.69

oscope

-0.69

ormal

-0.67

POSITIVE LOGITS

 recipes

1.03

Recipe

1.02

 recipe

1.01

Ingredients

1.01

 Recipes

0.89

 recip

0.81

reci

0.80

Override

0.76

Parser

0.76

Forge

0.75

Activations Density 0.048%

adaptations of recipes

mentions of recipes

No Comments

No Known Activations