INDEX

Explanations

recipes or instructions

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 @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

etime

-0.81

lasses

-0.79

osc

-0.74

usters

-0.73

 Stra

-0.72

phe

-0.72

emouth

-0.70

leaning

-0.70

ktop

-0.68

ormal

-0.68

POSITIVE LOGITS

 recipes

1.11

 recipe

1.04

Ingredients

0.99

Recipe

0.99

 Recipes

0.89

isine

0.84

reci

0.83

 ingredients

0.80

 recip

0.79

 ingredient

0.76

Activations Density 0.029%

recipes or instructions

mentions of recipes

No Comments

No Known Activations